Marketing Cloud Data

Management and Analytics

Salesforce, Winter ’24

@salesforcedocs
Last updated: September 15, 2023
© Copyright 2000–2023 Salesforce, Inc. All rights reserved. Salesforce is a registered trademark of Salesforce, Inc., as are other

names and marks. Other marks appearing herein may be trademarks of their respective owners.
CONTENTS

MARKETING CLOUD EINSTEIN AND ANALYTICS . . . . . . . . . . . . . . . . . . . . . . . 1

Analytics Builder . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
Collect Tracking Code . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 50
Intelligence Reports for Engagement . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 62
Google Analytics Integration for Marketing Cloud . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 191
Use Einstein to Improve Your Marketing Efforts . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 206
Salesforce Audience Studio and Data Studio . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 374

INDEX . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 376
MARKETING CLOUD EINSTEIN AND ANALYTICS

Import and manage data from multiple sources to gain deep insights into the behaviors and interests of your contacts across channels.
Use these insights to set marketing goals and refine customer journeys.

Analytics Builder
Analytics Builder enables you to gain deep insights into the behaviors and interests of your contacts across channels. Use these
insights to set marketing goals and refine customer journeys.
Collect Tracking Code
Collect Tracking Code is a JavaScript snippet you can use to capture data about known contacts and unknown visitor behavior. You
can use this data to enhance Contact profiles and optimize customer journeys across channels through predictive and personalized
recommendations. You can also update product and content catalog details in real time or to track email-driven revenue.
Intelligence Reports for Engagement
Intelligence Reports for Engagement enables you to generate, view, and share a detailed analysis of your Email, Push, and Journey
campaign-level data. Intelligence Reports for Engagement Advanced, a premium upgrade of Intelligence Reports, adds more features,
functionality, and analytics. The Advanced upgrade is available at an additional cost.
Google Analytics Integration for Marketing Cloud
This integration lets you track and analyze journey activity through your Google Analytics account without assistance from technical
support or services. You determine the URL tags and how data is collected and presented in the customizable Google Analytics
reporting dashboard. Use Google’s native authentication to securely link your Marketing Cloud and Google Analytics 360 or Google
Analytics Free accounts.
Use Einstein to Improve Your Marketing Efforts
AI for Marketing provides insights and data to inform the content and timing of your marketing activities. Use powerful Einstein
features to understand the engagement and behaviors of your customers so you can personalize every interaction.
Salesforce Audience Studio and Data Studio
View Salesforce Audience Studio and Data Studio documentation.

Analytics Builder
Analytics Builder enables you to gain deep insights into the behaviors and interests of your contacts across channels. Use these insights
to set marketing goals and refine customer journeys.
With Analytics Builder, you can:
• Measure engagement and performance of your email campaigns.
• Configure dashboard views to visualize data in flexible tables, charts, and graphs.
• Use Collect to view contact behaviors such as clicks and purchases.
• Create targeted audience based on predictive behavior models.
• Track each interaction in a journey and measure progress towards your target in a single interface within Journey Builder.

1
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Standard Reports for Marketing Cloud Data Management and Analytics

Marketing Cloud provides dozens of standard reports to track the effectiveness of your campaigns. You can run reports manually or
schedule them to run automatically. You can also choose who receives the reports.

SEE ALSO:
Standard Reports for Marketing Cloud Data Management and Analytics

Standard Reports for Marketing Cloud Data Management and Analytics

Marketing Cloud provides dozens of standard reports to track the effectiveness of your campaigns. You can run reports manually or
schedule them to run automatically. You can also choose who receives the reports.

Note: As of May 25, 2018, email reports that reference individual subscribers no longer include subscribers who were deleted
using the legacy Email Studio delete functionality.

Note: After a user's account is deactivated, the standard and discover reports that they created aren't accessible. Recreate the
reports.
A sending report failure is often due the attached report being larger than the maximum size.
1. To access the Reports feature, navigate to Analytics Builder and select Reports.
2. Select one of the standard reports:
• Email Studio
• Journey Builder
• MobileConnect
• MobilePush
• GroupConnect
• Microsites
• CloudPages
• Contacts
• MC Administration

3. Ensure that your report doesn’t exceed the maximum size of 6–7 MB. If so, use the Enhanced FTP option to send to recipients.

Get Started with Reports

The Reports Overview screen provides access to all reports available for Email Studio, Mobile Studio, CloudPages, SocialPages,
Microsites, JourneyBuilder, and Contact Counts.

SEE ALSO:
Contacts Count Report in Analytics Builder
Microsite Tracking
Email Studio Reports in Analytics Builder
Journey Builder Reports
Mobile Studio Reports

2
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Get Started with Reports

The Reports Overview screen provides access to all reports available for Email Studio, Mobile Studio, CloudPages, SocialPages, Microsites,
JourneyBuilder, and Contact Counts.
The Reports Overview screen includes the following:
• New Reports: Lists the newest reports available in the Marketing Cloud.
• Reports Shortcut: You can create and manage shortcuts to frequently used reports. Click Add Shortcut or Select Shortcuts to create
a new shortcut or click the x next to the shortcut to delete it.
• Reports Catalog: Lists all available reports. To view a brief description for each report, click View Catalog. To filter by category, click
on that category in the list to view a brief description of each report in that category only. Or you can click a recently run report to
view a brief description of that report.
• Saved Reports Menu: Click an item to populate the list to right with saved reports within that item's description.
• Saved Reports Grid: Lists all reports you have saved including relevant meta-data for each. You can filter and sort your view. Click the
name of the report to view the saved version or click Run to run a new version of the report.

Note: Discover reports are indicated by a blue cube icon and can only be accessed if you have Discover enabled in your account.

The Catalog screen provides a searchable list of available reports and a brief description of each. Click Create to run a new report.
The Activity Log screen provides detailed lists all reports running today, all scheduled reports, and the history of reports you have run.
This log includes both standard reports and Discover reports. Click View Parameters report setting details.

Create a Standard Report in Analytics Builder

Learn how to create and run a standard report in Marketing Cloud’s Report tool.
Marketing Cloud Analytics Builder Reports Frequently Asked Questions
Get the answers to frequently asked questions about the standard reports in Marketing Cloud Analytics Builder.

SEE ALSO:
Contacts Count Report in Analytics Builder
Microsite Tracking
Email Studio Reports in Analytics Builder
Journey Builder Reports
Mobile Studio Reports

Create a Standard Report in Analytics Builder

Learn how to create and run a standard report in Marketing Cloud’s Report tool.
1. Navigate to Analytics Builder and click Reports.
2. Click View Catalog for a list of available standard report templates.
3. Click Create next to the report you want to run.
4. Set report parameters. Options vary by report.

Tip: When you set a custom date range, the system generates a report based on data as it appears at 12:00 AM on that date.
To include data from the end date, set the end date parameter to the following day. For example, if you want to include data
from May 1 through the end of the day on May 17, set May 18 as the end date.

3
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

5. Click Submit.
6. Select an export or save option and complete the required fields.

Note: Where noted, some reports are not available as a web page and require you to select a format for file export. If you
want to email reports to more than one recipient, include their email addresses separated by commas.

7. Click Save.

Contacts Count Report in Analytics Builder

The Contact Count report contains information on the total number of contacts in an account, and it runs weekly. The report also
shows the Month End Report that runs on the last day of the month.
Contact Data Portability Report
View information included in the Contact Data Portability report for Contact Builder in Reports.
Microsite Tracking
The Microsite Tracking report displays tracking data from your microsite for a specific time frame you select. You can use this report
to help evaluate the effectiveness of your email campaigns in driving traffic to your landing pages. Compare the likelihood of readers
clicking one link rather than another. This report is available in the Reports tool.
Email Studio Reports in Analytics Builder
View a list and description of available Email Studio reports available in the Reporting tool.
Journey Builder Reports
View a list and description of Journey Builder reports available in the Reports tool.
Mobile Studio Reports
View a list and description of Mobile Studio reports available in the Reports tool.

Contacts Count Report in Analytics Builder

The Contact Count report contains information on the total number of contacts in an account, and it runs weekly. The report also shows
the Month End Report that runs on the last day of the month.

Important: To view this report, enable the Access permission under Contacts. Find this permission in the Reports Catalog section
of the Reports permission node.

Field Description
Total distinct contacts Number of distinct contacts used for billing purposes, it comprises:
• Count of unique Contact Keys regardless of the channel source
or method in which the contact entered Salesforce Marketing
Cloud. See Contact Definition and Count Determination in
Contact Builder for more information.
• Contact key counts in populations to whom no sends have
been attempted yet.

Distinct email addresses Number of distinct email addresses other than those addresses
deleted from the email channel. Unique email addresses used by
more than one subscriber are counted only one time in this
subtotal. This subtotal doesn’t apply to the formula that computes
Total Distinct Contacts.

4
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Description
MobilePush contacts Number of mobile device addresses. This count is only for reference
and doesn’t apply to the formula that computes total distinct
contacts.

MobileConnect contacts Number of mobile SMS numbers. This count is only for reference
and doesn’t apply to the formula that computes total distinct
contacts.

GroupConnect contacts Number of mobile LINE addresses. This count is only for reference
and doesn’t apply to the formula that computes total distinct
contacts.

Number of contacts in populations Contact key counts in populations to whom no sends have been
attempted yet.

Contacts from Triggered Sends Total number of contacts associated with triggered sends but not
associated with the All Subscribers list or another list in the
triggered send configuration. Contacts from triggered sends that
are performed at the child BU level aren’t included in Total Distinct
Contacts.

Leads from Sales and Service Clouds Number of leads synchronized from Sales and Service clouds using
Synchronized Data Sources in MC Connect.

Contacts from Sales and Service Clouds Number of contacts synchronized from the Sales and Service clouds
using Synchronized Data Sources in MC Connect.

Overlapping Leads and Contacts from Sales and Service Clouds Number of leads converted to contacts in the Sales and Service
clouds based on the two previous subtotals.

V2 Leads from Sales and Service Clouds Number of leads synchronized from Sales and Service Clouds using
version 3 or earlier of the Salesforce Connector.

V2 Contacts from Sales and Service Clouds Number of contacts synchronized from Sales and Service Clouds
using version 3 or earlier of the Salesforce Connector.

Leads, Contacts, and Accounts from Microsoft Dynamics CRM Number of leads, contacts, and accounts respectively synchronized
from Microsoft Dynamics CRM using the Dynamics CRM connector.

SEE ALSO:
Contacts Count Report in Analytics Builder
Create a Standard Report in Analytics Builder
Get Started with Reports
Get Started with Reports

Contact Data Portability Report

View information included in the Contact Data Portability report for Contact Builder in Reports.
This report contains information about a single contact record relation to data protection and privacy regulations. Use this report to
provide information to a data subject who requests a copy of their information.

5
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

• Subscriber information
• Email statistics
• Subscriber attributes
• MobilePush information and statistics, as applicable
• MobileConnect information and statistics, as applicable
• GroupConnect information, as applicable

Note: Run this report at the top level of your account.

SEE ALSO:
Create a Standard Report in Analytics Builder

Microsite Tracking
The Microsite Tracking report displays tracking data from your microsite for a specific time frame you select. You can use this report to
help evaluate the effectiveness of your email campaigns in driving traffic to your landing pages. Compare the likelihood of readers
clicking one link rather than another. This report is available in the Reports tool.
This five-part report provides details about views and clicks for a microsite you choose over a period you specify:
• Sheet 1: Microsite Activity

• Sheet 2: Landing Page Activity

• Sheet 3: Email Related Activity

• Sheet 4: Web Related Activity

• Sheet 5: Detailed Link Click Tracking

Microsite Activity
Learn about the information presented in this subsection of the Microsites Report in the Reports tool.
Landing Page Activity
Learn about this subsection of the Microsites Tracking report in the Reports tool.
Email Related Activity
Learn about the information contained in this subsection of the Microsites report in the Reports tool.
Web Related Activity
Learn about this subsection of the Microsites Tracking report in the Reports tool.
Detailed Link Click Tracking
Learn about this subsection of the Microsites Tracking report in the Reports tool.

Microsite Activity
Learn about the information presented in this subsection of the Microsites Report in the Reports tool.

Field Name Description

Unique Views Number of unique views received

6
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Description

Total Views Total number of views received

Unique Clicks Number of unique clicks received

Total Clicks Total number of clicks received

Landing Page Activity

Learn about this subsection of the Microsites Tracking report in the Reports tool.

Field Name Description

Page Name Name of the landing page tracked

Unique Views Number of unique views received

Total Views Number of views received

Unique Clicks Number of unique clicks received

Total Clicks Number of clicks received

Email Related Activity

Learn about the information contained in this subsection of the Microsites report in the Reports tool.

Field Name Description

Email Name Name of the email containing a link to the microsite

Job ID Job ID of the email send tracked in this row

Send Time Send time of the email.

Unique Views Number of unique views of a landing page that resulted from this
email send. Multiple views by the same person would be counted
only once.

Total Views Number of views of a landing page that resulted from this email
send. Multiple views by the same person contribute to this total.

Unique Clicks Number of unique clicks of links in a landing page that resulted
from this email send. Multiple clicks by the same person would be
counted only once.

Total Clicks Number of clicks for links in a landing page that resulted from this
email send. Multiple clicks by the same person contribute to this
total.

Web Related Activity

Learn about this subsection of the Microsites Tracking report in the Reports tool.

7
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Description

Page Name Name of the landing page tracked

Unique Views Number of unique views from web traffic other than links in emails;
multiple views by the same person would be counted only once.

Total Views Number of views from web traffic other than links in emails;
multiple views by the same person contribute to this total.

Unique Clicks Number of unique clicks on the landing page from web traffic other
than links from emails; multiple clicks by the same person would
be counted only once.

Total Clicks Number of clicks on the landing page from web traffic other than
links from emails; multiple clicks by the same person contribute to
this total.

Detailed Link Click Tracking

Learn about this subsection of the Microsites Tracking report in the Reports tool.

Field Name Description

Page name Name of the landing page tracked

URL URL for the link clicked on the landing page

Link Alias Tracking alias for the link clicked on the landing page

Unique Clicks Number of unique clicks of the link; multiple clicks by the same
person would be counted only once.

Total Clicks Number of clicks for the link; multiple clicks by the same person
contribute to the total

Email Studio Reports in Analytics Builder

View a list and description of available Email Studio reports available in the Reporting tool.
To create a standard Email Studio report, see Create a Standard Report in Analytics Builder.

Report Name Description

A/B Test Summary Contains summary and comparison information about one or more A/B test campaigns for the
date range you specify.

Account Send Summary Displays all potential response counts or rates for an account organized by send. Enterprise or
reseller reports also display respective member results organized by account.

Attribute by Tracking Event Displays how your subscribers reacted to a certain email send, based on a specific tracking event,
and a particular attribute.

8
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Report Name Description

Campaign Email Job Tracking Displays the email tracking data for each job sent that is associated with the selected campaign.
Summary Use this report to get a complete list of all sends in a campaign and a quick summary of all relevant
email tracking statistics.

Campaign Email Tracking Use this report to quickly see email level tracking statistics if the emails in your campaign are sent
Summary in more than one job. This report displays the send tracking data for a specific campaign. Displays
the email tracking data for each email associated with the campaign. If an email is sent through
multiple jobs, Analytics Builder summarizes the tracking data for each job by email.

Carrier Deactivation Summary Use this report to both verify the accuracy of the opt-out process and insight into customers to
Report potentially retarget for SMS opt-in. The report displays a daily and historic overview of the
subscriptions updated within your account. The updates are a result of deactivated phone numbers
on the carrier’s network or numbers ported from one carrier to another.

Conversion Tracking Statistics Displays all conversion activity across all your email sends over a specific time period.

Email Message Frequency This report cannot be viewed as a web page. Includes the number of customers received multiple
email messages from period to period for comparison purposes. The available periods for
comparison are: Yesterday vs. Day Before; Previous 2 Weeks Before Today; Previous Sunday to
Sunday Weeks; Last 30 days vs. Previous 30 days; Previous 2 calendar months.

Email Performance by Attribute Lets you evaluate email send results for different subscriber attribute and preference values.

Email Performance by Domain Enables you to evaluate email send results for each domain sent to for a single send.

Email Performance by List Enables you to assess response, bounce, and click-through rate for each list or group. The rate can
be sent to as part of a send event that excludes email sent to a single recipient.

Email Performance for All Domains Enables you to evaluate email send results for each domain sent to for a single send.

Email Performance Over Time Shows data for all sends during a specific period.

Email Send Shows how many emails have been sent from each of your accounts. This report can be run for
any time period, present, or past.

Email Sends by User Displays a list of account users who have sent emails during the specified date range and the total
number of emails that each user has sent.

Email Send Performance by Shows send performance data by audience segment.

Audience Builder Segment

Forwarding Activity Details Displays details for emails that are forwarded from subscribers to other individuals.

Impression Tracking by Job Displays the number of times the content area was sent as part of a job. The count could be the
number of impressions and the link performance for links found within the impression region.

Impression Tracking for Triggered Displays the performance of an impression region for triggered sends by a time period you choose.
Send by Period

List Demographics Enables you to analyze your lists to see a breakdown of subscribers by status, domain, and
subscription tool.

List Performance Over Time Enables you to examine each of your lists to evaluate their effectiveness over time across multiple
sends.

9
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Report Name Description

List Size Over Time Displays the number of subscribers on a list over a specified time period. Includes a table showing
the number of subscribers by status for each month in the specified time period. This data is also
provided in a line graph.

Multi-Campaign Tracking Use this report to compare email performance across multiple campaigns. This report shows that
Summary email tracking summarized by campaign for all campaigns with a deployment date. The report
shows tracking by the selected date range and the total of all selected campaigns for each tracking
category.

Recent Email Sends Summary Enables you to analyze a summary of your recent account activity.

Region Performance for Triggered Displays how a single section of content performs over a period across multiple triggered send
Sends Over Time jobs.

Region Performance Over Time Displays how a single section of content performs over a period across multiple jobs.

Response Trend Analysis for Email Displays how an email send has performed over a specified date range.
Send

Send Classification by Email Enables you to compare the send performance data of transactional and commercial sends.
Tracking Report

Sendable Data Extension Includes charts which show subscriber status breakdown and a top-level view of which domains
Demographics are best represented in the selected sendable data extension.

Sendable Data Extension Provides an analysis of a sendable data extension over time. You can use this report to evaluate
Performance Over Time when a previously effective data extension is no longer effective.

Single Email Performance by Summarizes email open and click activity on mobile vs. desktop devices for an email. This report
Device shows the percentage of opens, unique opens, and clicks occurring on mobile devices.

Spam Complaints Over Time Provides historical data about received spam complaints.

Subscriber Engagement Displays which subscribers are most or least engaged with emails.

Subscriber Most Recent Activity Displays a list of all subscribers and details their most recent open or click activity.

Subscribers Not Sent To Displays a list of subscribers who have not received an email during a specified date range.

Triggered Sends Tracking Displays detailed tracking data for a single triggered send over a custom time frame.

Note: The overlay option is not available under the Click Activity tab.

Unengaged Subscribers for a List Displays which subscribers on a specified list are unresponsive after multiple emails sends.

A/B Test Summary

The A/B Test Summary contains summary and comparison information about one or more A/B test campaigns for the date range
you specify.
Account Send Summary
Displays all potential response counts or rates for an account organized by send. Enterprise or Reseller reports also display respective
member results organized by account.

10
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Attribute by Tracking Event Report for Email Studio in Analytics Builder

Use the Attribute by Tracking Event Report for Email Studio in Analytics Builder to check how your subscribers reacted to a certain
email send. The report lists the subscribers who interacted with an email send during the timeframe you select. Choose a subscriber
attribute to include in the report. The report works only with values of the chosen attribute at the time of reporting and not the value
at the time of send. For example, use this report to evaluate the effectiveness of a campaign in generating subscriber clicks for men
versus women.
Campaign Email Tracking
The Campaign Email Tracking report shows send tracking data for a specific campaign.
Carrier Deactivation SMS Summary
Some US wireless carriers produce daily files for phone numbers that have deactivated from their network or been ported from one
carrier to another. Marketing Cloud changes the status for all numbers included in that file from Opted-In to Opted-Out.
Conversion Tracking Statistics
Run this report to compare the effectiveness of links within campaigns or the effectiveness of campaigns in number and value of
conversions. This report contains a list of conversions for links included in emails across multiple sends during a time frame.
Email Performance by Attribute Report in Analytics Builder
Run this report to view data for a specific subscriber included in a specific send. This report runs against Legacy List-Based Attributes
only and doesn’t account for the Sendable DEs field. To display the relevant data, give the Sendable DEs field the same name and
ensure that the data is within the Legacy List-Based Attributes.
Email Performance by Domain
This report provides data for the top 10 email domains for an email send. Use this report to analyze how domains responded to a
particular email send.
Email Performance by List
This report contains graphics to illustrate Emails Sent by List, Open Rate by List, Bounce Rate by List, and Click Through Rate by List.
This report shows only unique opens and clicks. Use this report to analyze which lists responded most favorably to a particular email
send.
Email Performance for All Domains
This report shows performance data for each email domain included in sends during a specific period. You can use this analysis
identify domains that are bouncing your email so you can begin to resolve the delivery issue.
Email Performance Over Time
This report shows data for all sends during a specific period. You can use this report to evaluate when a previously effective email is
no longer effective.
Email Send Performance by Audience Builder Segment Report
Use the Email Send Performance in Marketing Cloud Audience Builder Segment report to see send performance data by audience
segment. To compare the send performance of segments in a segmented audience, run this report.
Email Send
Use the Email Send report to view account activity. This report is often used by Agency users for billing their child accounts. Enterprise
users can also use this report to view the activity of their Lock and Publish accounts.
Email Sends by User
Learn about the information provided in the Email Sends by User report.
Forwarding Activity Details
Use this report to analyze forwarding activity for your email sends. You can use this report to enable providing incentives to subscribers
whose forwarded emails result in new subscribers.

11
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Track Impressions by Job Report for Email Studio in Analytics Builder

The Impression Tracking by Job report for Email Studio in Marketing Cloud Analytics Builder is two reports combined into one. The
Job Summary section shows overview tracking information. The Impression Tracking Details section lists the different areas of the
report that contained impression tracking and contains data for each area. You can only track emails that use dynamic content or
AMPscript .
Impression Tracking for Triggered Sends Report in Analytics Builder
Use the Impression Tracking for Triggered Sends report for Email Studio in Marketing Cloud Analytics Builder to monitor triggered
sends over a specific time. You can only track emails that use dynamic content or AMPscript.
List Demographics
This report displays the status, subscription method, and domains of the subscribers on a list. Use this report to see what percentage
of your subscribers are using a certain domain.
List Performance Over Time
This report provides statistics for all sends to a list during a specified time period.
List Size Over Time Report for Email Studio in Analytics Builder
To check how your list grows and subscriber statuses change over time, use the List Size Over Time report in Marketing Cloud
Analytics Builder. Because the data shows first-time events for a status change, there could be overlap of data. Also, more than one
event or status can occur with a subscriber in the time period you define. The report shows you the most recent status change that
occurred during the specified time.
Multi-Campaign Email Tracking Summary
This report shows the Email Tracking by campaign, for all campaigns during the selected date range. The report also includes a grand
total of all selected campaigns for each tracking category. Use this report to compare the email performance across multiple
campaigns.
Recent Email Sending Summary
The Recent Email Sending Summary provides a summary of your account activity over a recent period. You can use this report to
confirm that your jobs were completed successfully.
Region Performance for Triggered Sends Over Time
This report shows how a single section of content performs over time across multiple jobs in Triggered Emails.
Region Performance Over Time
The Region Performance Over Time report shows how a single section of content performs over a period across multiple sends. You
can use this report to see how a specific link is performing over a certain period. Only emails that contain dynamic content or
AMPscript can be tracked in this report.
Response Trend Analysis for an Email Send
Use this report to analyze when subscribers respond to your email relative to when you send it. For example, if you want to send an
announcement of an event at a specific time, you can run this report against other sends to determine how far in advance you must
send the message to ensure that most your subscribers open it.
Send Classification by Email Tracking
This report shows the send performance data of transactional and commercial sends. Use this report when you want to compare
the send performance data of transactional and commercial sends.
Single Email Performance by Device
The Single Email Performance by Device report displays email performance on mobile devices versus desktop devices.
Spam Complaints Over Time
This report provides historical data on the level of spam complaints received.

12
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Subscriber Engagement
Use this report to identify your most engaged subscribers. You could target these subscribers for special offers. This report includes
the number of emails that you have sent each subscriber over a specified period, and the number of emails the subscriber has
opened or clicked.
Subscriber Most Recent Activity
The Subscriber Most Recent Activity report shows when each subscriber last opened or clicked a message.
Subscribers Not Sent To
This report shows a list of emails for subscribers who weren’t included in a send during a time frame that you select.
Triggered Sends Tracking
The Triggered Sends Tracking report contains standard tracking information for a triggered send over a time period. You can use
this report to determine the effectiveness of a triggered send in producing opens and clicks and not causing unsubscribes.
Unengaged Subscribers for a List
This report shows a list of your most inactive subscribers. Use this information to target certain lists or subscribers or to clean up your
lists.

SEE ALSO:
Email Studio

A/B Test Summary

The A/B Test Summary contains summary and comparison information about one or more A/B test campaigns for the date range you
specify.

Note: This report cannot be viewed as a webpage. Choose a format for export.

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Account Send Summary

Displays all potential response counts or rates for an account organized by send. Enterprise or Reseller reports also display respective
member results organized by account.
This report shows total send and response data for your account. To see the same data differentiated by email send, go to the second
page and view the Delivery Log. The Delivery Log lists the same fields as in the Account Send Summary for each send you performed
during the time interval you defined. All numeric data relates to the sends that occurred during the defined interval. For example, if there
is an ask for yesterday's data, the Open or Click that happened yesterday but relates to a send that occured two days ago is not counted.

Field Name Description

Client Name Name of your company

Client ID Your account ID number

Sends Number of emails sent from your account during the time interval
you defined

13
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Description

Implicit Deliveries Number of emails that did not receive bounces and are assumed
delivered during the time interval you defined

Implicit Delivery Rate Percentage of delivered emails over bounced emails during the
time interval you defined

Overall Bounces Number of bounces your account has received in the time interval
you defined; includes all hard, soft, technical, and unknown
bounces.

Overall Bounce Rate Percentage of emails sent that bounced during the interval you
defined

Hard Bounces Number of hard bounces your account received during the interval
you defined

Hard Bounce Rate Percentage of emails that experienced hard bounces during the
interval you defined

Soft Bounces Number of soft bounces received during the interval you defined

Soft Bounce Rate Percentage of emails that experienced soft bounces during the
interval you defined

Block Bounces Number of block bounces received during the interval you defined

Block Bounce Rate Percentage of emails that experienced technical bounces during
the interval you defined

Technical Bounces Number of technical bounces received during the interval you
defined

Technical Bounce Rate Percentage of emails that experienced block bounces during the
interval you defined

Unknown Bounces Number of unknown bounces received during the interval you
defined

Unknown Bounce Rate Percentage of emails that experienced unknown bounces during
the interval you defined

Unique Opens Number of unique opens received during the interval you defined.
A unique open means one open per person.

Cumulative Opens Number of opens received during the interval you defined. If one
subscriber opened your email multiple times, that number is
recorded here.

Open Rate Percentage of emails opened during the interval you defined. This
number is calculated by dividing the Unique Opens by Implicit
Deliveries.

Unique Clicks Number of unique clicks received in the emails sent during the
interval you defined; one click per subscriber

14
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Description

Cumulative Clicks Total number of clicks received in the emails sent during the interval
you defined

Click Rate Percentage of clicks received over the number of subscribers sent
to. This number is calculated by dividing The Unique Clicks by the
Implicit Deliveries.

Unique Survey Responses Number of unique responses received from surveys during the
interval you defined. Unique responses means one response per
person.

Cumulative Survey Responses Number of responses received from surveys during the interval
you defined. If one person responded more than once, that number
is recorded here.

Survey Response Rate Percentage of surveys that received responses during the interval
you defined. This number is calculated by dividing Unique Survey
Responses by Implicit Deliveries.

Unique Conversions Unique number of conversions received during the interval you
defined; one conversion per subscriber. See Conversion Tracking
Statistics for more information.

Cumulative Conversions Number of conversions received during the interval you defined.

Conversion Rate Percentage of conversions received. This number is calculated by

dividing Unique Conversions by Implicit Deliveries.

Unique FTAFs Number of unique subscribers who clicked the Forward to a Friend
icon in your emails during the interval you defined. Unique FTAFs
means one click per person.

Cumulative FTAFs Number of times subscribers clicked the Forward to a Friend icon
in your emails during the interval you defined. If one subscriber
forwarded the email multiple times, that number is recorded here.

FTAF Rate Percentage of emails that your subscribers forwarded during the
interval you defined.

Unique FTAF Recipients Number of times your subscribers forwarded your emails to during
the interval you defined. For example, if one subscriber clicked the
FTAF icon and forward the email to five people, only one instance
is recorded here.

Cumulative FTAF Recipients Number of individuals your subscribers forwarded your emails to
during the interval you defined. For example, if one subscriber
clicked the FTAF icon and forwarded the email to five people, each
of those individuals is recorded here.

FTAF Recipient Rate Percentage of forwarded emails. This number is calculated by taking
the Unique FTAF Recipients number over the Total Delivered.

15
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Description

Unique FTAF Subscribers Number of individuals who subscribed to your lists as a result of a
subscriber clicking the Forward to a Friend icon during the interval
you defined.

FTAF Subscriber Rate Percentage of people who subscribed after receiving the forwarded
email as compared to people who did not subscribe. This number
is calculated by dividing FTAF Recipient Rate by Implicit Deliveries.

Complaint Deliveries Number of emails delivered to domains for which complaints were
received. For example, if you sent 300 emails to example.com and
one of those emails received a spam complaint, the number listed
here would be 300.

Unique Complaints Number of unique spam complaints your account received during
the interval you defined; one complaint per subscriber

Cumulative Complaints Number of spam complaints your account received during the
interval you defined. Each time a subscriber complaint, this number
increases.

Complaint Rate Percentage of emails that received spam complaints during the
interval you defined.

Unique Unsubscribes Unique number of unsubscribes received during the interval you
defined. Unique unsubscribes means that if one subscriber
unsubscribes from more than one email list, only one instance is
recorded here.

Cumulative Unsubscribes Number of unsubscribes received during the interval you defined.

Unsubscribe Rate Percentage of subscribers who unsubscribed as compared to

people who did not during the interval you defined. This number
is calculated by dividing Unique Unsubscribes by Implicit Deliveries.

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Attribute by Tracking Event Report for Email Studio in Analytics Builder

Use the Attribute by Tracking Event Report for Email Studio in Analytics Builder to check how your subscribers reacted to a certain email
send. The report lists the subscribers who interacted with an email send during the timeframe you select. Choose a subscriber attribute
to include in the report. The report works only with values of the chosen attribute at the time of reporting and not the value at the time
of send. For example, use this report to evaluate the effectiveness of a campaign in generating subscriber clicks for men versus women.

Field Name Description

Subscriber Key Unique ID for the subscriber

Tracking Activity The tracking activity included on the account. Valid values include:

16
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Description

• All

• Bounce

• Open

• Click

• Unsubscribe

Event Time Date and time tracking activity occurred

[Attribute] Subscriber attribute you chose; valid selections include subscriber

attributes defined in your account

Default Default value you set when you created the attribute; if no default
value is defined, an asterisk appears.

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Campaign Email Tracking

The Campaign Email Tracking report shows send tracking data for a specific campaign.

Note: Triggered Sends tracking information is not included in this report.

Field Name Description

Email Name Name of the email sent to this list

Send Date Date of the email send

Send Total number of emails sent

% of Send Percentage of total emails sent

Opens Number of emails opened

Open Rate Percentage of emails opened

Clicks Total number of email clicks

Click Rate Percentage of clicks received over the number of subscribers sent
to. This number is calculated by dividing The Unique Clicks by the
Implicit Deliveries.

Bounces Total number of emails bounced

Bounce Rate Percentage of emails sent that bounced

Unsubscribes Number of emails included in the send that resulted in unsubscribes

17
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Description

Unsubscribe Rate Percentage of subscribers who unsubscribed as compared to
people who did not. This number is calculated by dividing Unique
Unsubscribes by Implicit Deliveries.

Shares Total number of shares the send received

Delivered Number of successfully delivered emails included in this list

Delivery Rate Percentage of messages delivered

Conversions Number of conversions received during the interval you defined

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Carrier Deactivation SMS Summary

Some US wireless carriers produce daily files for phone numbers that have deactivated from their network or been ported from one
carrier to another. Marketing Cloud changes the status for all numbers included in that file from Opted-In to Opted-Out.
The Carrier Deactivation SMS Summary displays a daily and historic overview of the subscriptions updated in your account. This standard
report is available for all marketers using MobileConnect with U.S. short codes. The report shows an overview up to the 90 days from
when the report was created.
Contact your Marketing Cloud account executive for details regarding the specific activation date of Carrier Deactivation File Processing
within your account.

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Conversion Tracking Statistics

Run this report to compare the effectiveness of links within campaigns or the effectiveness of campaigns in number and value of
conversions. This report contains a list of conversions for links included in emails across multiple sends during a time frame.

Note: Conversion Tracking must be enabled on your account and implemented in the email to use this feature. Contact your
account executive to learn more.

Field Name Description

[Link Name] Tracking alias of the link

Email Address Email address of the subscriber whose conversion is tracked

Conversion date and time Date and time of the conversion

Total Dollar value of the conversion

Link Total Total dollar value for the link

18
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Description

Email Total Total dollar value from the email send

Account Total Total dollar value for the account

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder
Implement Conversion Tracking

Email Performance by Attribute Report in Analytics Builder

Run this report to view data for a specific subscriber included in a specific send. This report runs against Legacy List-Based Attributes
only and doesn’t account for the Sendable DEs field. To display the relevant data, give the Sendable DEs field the same name and ensure
that the data is within the Legacy List-Based Attributes.

Field Name o
nip
tirD
cse
Email Name emaN
f o
tnetnoc
n i
eh t
l imae
dnes

Email Send Date e t aD

f o
dnes

Attribute Selected ebutirtAt

atad
s i
desab
n o

Attribute Value ci f icpeS

eulav
f o
eh t
ebutirtta

Send Count latoT

rem
bun
f o
sl m
iea
tnes

% if Send egatnecreP
f o

19
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name o
nip
tirD
cse
latot
sl miea
tnes

Opens rem
buN
f o
sl m
iea
denepo

Open Rate egatnecreP

f o
sl m iea
denepo

Clicks latoT
rem
bun
f o
l imae
skci lc

Click Rate egatnecreP

f o
skci lc
deviecer
revo
eh t
rem bun
f o
sbreircubs
tnes
. ot
s ihT
rem bun
s i
detaulclac
y b
gnidivid
eh T
euqinU
skci lC
y b
eh t
ticm iIpl
.esievriDel

Bounce latoT
rem
bun
f o

20
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name o
nip
tirD
cse
sl miea
decnuob

Bounce Rate egatnecreP

f o
sl m iea
tnes
taht
decnuob

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Email Performance by Domain

This report provides data for the top 10 email domains for an email send. Use this report to analyze how domains responded to a particular
email send.

Field Name Description

Domain Name Name of the recipient domain for the email send

Emails Sent Total number of emails sent to the domain

Emails Delivered Number of emails delivered to the domain

% of Total Send Percentage of total emails that were sent to the domain

Bounce Rate Domain bounce rate

Open Rate Domain open rate

Click Through Rate Click-through rate for emails sent to the domain

Unsubscribe Rate Unsubscribe rate for emails sent to the domain

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Email Performance by List

This report contains graphics to illustrate Emails Sent by List, Open Rate by List, Bounce Rate by List, and Click Through Rate by List. This
report shows only unique opens and clicks. Use this report to analyze which lists responded most favorably to a particular email send.

Field Name Description

List Name Name of the list used in the email send

21
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Description

Send Count Total number of emails sent to the list

% of Total Send Percentage of total emails that were sent to the list

Bounce Rate Bounce rate for emails sent to the list

Open Rate Open rate for emails sent to the list

Click Through Rate Click-through rate for emails sent to the list

Unsubscribe Rate Unsubscribe rate for emails sent to the list

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Email Performance for All Domains

This report shows performance data for each email domain included in sends during a specific period. You can use this analysis identify
domains that are bouncing your email so you can begin to resolve the delivery issue.

Note: This report only works for standard Email Studio emails. It doesn’t work for triggered emails or journey emails.

Field Name Description

Domain Name Name of the domain used in the email send

Email Sent Total number of emails sent to the domain

% of Total Sent Percentage of total emails sent to the domain

Delivered Number of delivered emails sent to the domain

Bounce Number of bounced emails sent to the domain; includes all

bounces for all subscribers.

Bounce % Bounce rate for emails sent to the domain

Opened Number of opened emails sent to the domain; contains all opens
for all subscribers

Open % Open rate for emails sent to the domain

Clicked Number of emails sent to the domain that received clicks; includes
all clicks for all subscribers

Click % Click-through rate for emails sent to the domain

Unsubscribed Number of emails sent to the domain that resulted in the recipient
unsubscribing; contains all unsubscribes for all subscribers

22
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Description

Unsubscribe Rate Unsubscribe rate for emails sent to the domain

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Email Performance Over Time

This report shows data for all sends during a specific period. You can use this report to evaluate when a previously effective email is no
longer effective.

Field Name Description

Date and Time Sent Date and time of the email send

Send Count Number of emails in the email send

Delivered Number of emails in the email send that were not undeliverable

Undeliverable Number of emails in the email send returned as undeliverable

Unique Opens Number of opened emails in the email send; each email only
counted once

Unique Clicks Number of emails in the email send that were clicked; each email
only counted once

Unsubscribes Number of emails in the email send that resulted in unsubscribes

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Email Send Performance by Audience Builder Segment Report

Use the Email Send Performance in Marketing Cloud Audience Builder Segment report to see send performance data by audience
segment. To compare the send performance of segments in a segmented audience, run this report.
The report contains the following parameters:
• Segment Name
• Sends
• Percent of Send
• Opens
• Open Rate
• Clicks
• Click Rate

23
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

• Bounces
• Bounce Rate
• Unsubscribes
• Unsub Rate

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Email Send
Use the Email Send report to view account activity. This report is often used by Agency users for billing their child accounts. Enterprise
users can also use this report to view the activity of their Lock and Publish accounts.

Field Name Description\

ParentID Parent account ID

Parent Name Parent account name

Member ID Account ID of the child or lock-and-publish account

Member Name Name of the child or lock-and-publish account

Account Type Account type of the child or lock-and-publish account

[Interval] Account activity for the specified interval; for example, if you select
Month, an interval column appears for each month in the period
the report covers.

Total (all periods) Total account activity for the time period the report covers

Total [Parent Name] [Interval] Total activity for the accounts in the time interval

Total [Parent Name] Total (all periods) Total activity for the accounts for the time period the report covers

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Email Sends by User

Learn about the information provided in the Email Sends by User report.

Note: You must have administrator permissions to run this report. This report does not contain data for your Lock and Publish
accounts.

Field Name Description

Job ID ID number of the email send

Email Name Name of content in the email send

24
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Description

Email Subject Subject line of the email send

Delivered Time Time of the email send

BCC Number of blind copies of the email sent in the email send.

Count Number of emails sent excluding blind copies

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Forwarding Activity Details

Use this report to analyze forwarding activity for your email sends. You can use this report to enable providing incentives to subscribers
whose forwarded emails result in new subscribers.

Field Name Description

Forwarding Subscriber Subscriber who forwarded the email using the Forward-to-a-Friend
feature

New Subscriber If the person who received the forwarded email subscribed to the
list as a result, their email address appears in this column.

Time Forwarded Date and time the message was forwarded

Comments Comments the subscriber included when forwarding the email

using the Forward-to-a-Friend feature

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Track Impressions by Job Report for Email Studio in Analytics Builder

The Impression Tracking by Job report for Email Studio in Marketing Cloud Analytics Builder is two reports combined into one. The Job
Summary section shows overview tracking information. The Impression Tracking Details section lists the different areas of the report
that contained impression tracking and contains data for each area. You can only track emails that use dynamic content or AMPscript .
To use this report, enable impression tracking by contacting Salesforce support.

Note: Only admins can run this report.

1. Select and run the report.

2. Be aware of the information in the different sections:

25
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Table 1: Job Summary

Field Name Description
Event Occurrence tracked

Unique Number of unique occurrences per link in the impression region

Total Total number of occurrences

Percentage Percentage of Unique Clicks divided by Impression Sent for that

region

Table 2: Impression Tracking Details

Field Name Description
Region Name Name of impression region you are tracking

Link Name Name of linked image or text

Impressions Sent Number of impression regions sent

Unique Clicks Number of unique clicks a link receives

Total Clicks Total number of clicks a link receives

Region CTR(Click Through to Read) Percentage of unique clicks compared to the number of
impressions sent

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Impression Tracking for Triggered Sends Report in Analytics Builder

Use the Impression Tracking for Triggered Sends report for Email Studio in Marketing Cloud Analytics Builder to monitor triggered sends
over a specific time. You can only track emails that use dynamic content or AMPscript.

Note: Only admins can run this report.

The report relies on click and JobURL data. If the dynamic content has no URLs or clicks, the Impression Tracking Details section is empty.

Table 3: Send Summary

Field Name Description
Event Occurrence being tracked

Unique Number of unique occurrences for every event listed. For example,
if the Delivered field shows 4, it means that four triggered emails
were delivered during the report period.

Total Total number of occurrences

26
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Description

Percentage Percentage of the event to the total number of delivered emails
for the report period

Table 4: Impression Tracking Details

Field Name Description
Region Name Name of the impression region tracked

Link Name Name of the linked image or text

Impressions Sent Number of impression regions that were sent

Unique Clicks Number of unique clicks a link receives

Total Clicks Total number of clicks a link receives

Region CTR (Click Through to Read) Percentage of unique clicks compared to the number of
impressions sent

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

List Demographics
This report displays the status, subscription method, and domains of the subscribers on a list. Use this report to see what percentage of
your subscribers are using a certain domain.

Field Name Description

Status Number of subscribers in each status

Count Number of unsubscribed or deleted subscribers

Percent Percentage of unsubscribed or deleted subscribers

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

List Performance Over Time

This report provides statistics for all sends to a list during a specified time period.

Field Name Description

Email Name Name of the email sent to this list

27
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Description

Date and Time Sent Date and time the email was sent to this list

Send Count Number of emails included in the send to the list

Delivered Number of successfully delivered emails included in this list

Unique Opens Number of opened emails included in the send; each email is only
counted once

Unique Clicks Number of clicked emails included in the send; each email is only
counted once

Unsubscribes Number of emails included in the send that resulted in unsubscribes

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

List Size Over Time Report for Email Studio in Analytics Builder
To check how your list grows and subscriber statuses change over time, use the List Size Over Time report in Marketing Cloud Analytics
Builder. Because the data shows first-time events for a status change, there could be overlap of data. Also, more than one event or status
can occur with a subscriber in the time period you define. The report shows you the most recent status change that occurred during
the specified time.

Tip: Accuracy of this report improves over longer periods. We recommend using it to measure list growth over a period of one
month or longer.

Note: A full inbox could cause a subscriber to move in and out of the Bounced and Held statuses.

When you create the report, you can select all subscribers, my list, or my groups. For the Child business unit, the All Subscribers option
is not available when creating the report. Enable All Subscribers Access to use the options for a Child business unit.

Field Name Description

Added Subscribers added for the report period

Bounced Subscribers who experienced a bounce for the first time during
the report period

Undeliverable Subscribers whose email address was marked as Undeliverable

during the report period

Unsubscribed Subscribers who opted out of the list during the report period

Active Number of subscribers in the list that are not in a status of Bounced,
Undeliverable, or Unsubscribed at the end of the report period

28
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Note: You cannot reconcile counts by adding or subtracting Added, Bounced, Undeliverable, and Unsubscribe counts to a previous
Active total to match a newer Active total.

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Multi-Campaign Email Tracking Summary

This report shows the Email Tracking by campaign, for all campaigns during the selected date range. The report also includes a grand
total of all selected campaigns for each tracking category. Use this report to compare the email performance across multiple campaigns.

Field Name Description

Campaign Name Name of the campaign to which the emails belong

Campaign Description Description of the campaign

Deployment Date Campaign start date

Campaign Owner Person managing the campaign

Send Count Total emails send as part of this campaign

% of Send Percentage of total emails sent

Opens Number of emails opened

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Recent Email Sending Summary

The Recent Email Sending Summary provides a summary of your account activity over a recent period. You can use this report to confirm
that your jobs were completed successfully.

Field Name Description

Job ID Email send ID

Name Name of email content in this email send

Subject Subject line of this email send

Send Start Time Date and time the email send started

Send Complete Time Date and time the email send was completed

Emails Sent Number of emails included in the email send

Emails Delivered Number of emails not returned as undeliverable; calculated by

subtracting the Undeliverable value from the Emails Sent value.

29
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Description

Undeliverable Number of bounced emails

Survey Responses Number of survey responses

Total Click Throughs Number of resulting clicks; includes multiple clicks by the same
subscriber

Unique Click Throughs Number of emails clicked in this email send; includes a click by
each subscriber only once

Unique Emails Opened Number of emails opened in this email send; includes each email
only once per subscriber

Unsubscribes Number of unsubscribes from this email send

FTAF Forwarders Number of subscribers who forwarded the email at least once

FTAF Recipients Number of recipients who received the forwarded email

FTAF Subscribers Number of recipients who subscribed to a list in response to

receiving a forwarded email

Open Rate Percentage of Emails Delivered that were Emails Opened

Deliverability Rate Percentage of Emails Delivered

Bounce Rate Percentage of Emails Delivered that were Emails Bounced

Unsubscribe Rate Percentage of Emails Delivered that were Unsubscribes

Unique Click Through Rate Percentage of Emails Delivered that resulted in Unique Click
Throughs

Unique Complaints Number of complaints the email send received; includes one
complaint per subscriber.

Cumulative Complaints Number of spam complaints this email send received; if one
subscriber sent more than one complaint, that number is included
here.

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Region Performance for Triggered Sends Over Time

This report shows how a single section of content performs over time across multiple jobs in Triggered Emails.

Note: You must be an administrator to run this report.

Field Name Description

Performance by Link in Region Region the report is tracking

30
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Description

Link Alias or URL Link in the region that is being tracked. You specify the Link Alias
when you create the link in the email. The URL appears if you don't
specify a link alias.

Triggered Send Name of the send that was triggered

Impressions Sent Number of links that were sent in an email send using dynamic
content

Unique Clicks Number of recipients who clicked the link

Total Clicks Total number of clicks on the link. Multiple clicks from the same
subscriber are counted.

Click Percentage Percentage of Unique Clicks divided by Impression Sent

Example: Twelve subscribers subscribed to Northern Trails' email list in May. Northern Trails wants to track how a link in the
welcome email that was sent automatically performed for all 12 subscribers. They ran a Region Performance for Triggered Sends
Over Time report and saw how the link performed in each individual email and its overall performance.

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Region Performance Over Time

The Region Performance Over Time report shows how a single section of content performs over a period across multiple sends. You can
use this report to see how a specific link is performing over a certain period. Only emails that contain dynamic content or AMPscript can
be tracked in this report.

Note: You must be an administrator to run this report.

Field Name Description

Performance by Link in Region Region tracked in this report

Link Alias or URL The link in the region that is being tracked. You specify the Link
Alias when you create the link in the email. The URL only appears
if you do not specify a link alias.

Job ID ID of the email send

Send Date Date and time of email send

Impressions Sent Number of links that were sent in an email send using dynamic
content

Unique Clicks Number of recipients who clicked the link

Total Clicks Total number of clicks on the link; multiple clicks from the same
subscriber are counted.

31
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Description

Click Percentage Percentage of Unique Clicks divided by Impression Sent

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Response Trend Analysis for an Email Send

Use this report to analyze when subscribers respond to your email relative to when you send it. For example, if you want to send an
announcement of an event at a specific time, you can run this report against other sends to determine how far in advance you must
send the message to ensure that most your subscribers open it.

Field Name Description

Interval Start Time Interval, selected by you, into which the responses are divided on
the report

Sent Number of emails sent during this interval; the gray column is a
cumulative total of emails sent for all intervals to that point

Bounced Number of emails bounced during this interval; the gray column
is the cumulative total of bounces for all intervals to that point

Unique Opened Number of subscribers who opened the email during this interval;
the gray column contains the cumulative total of opens for all
intervals to that point. These values count only the first time a
subscriber opens an email.

Opened Number of emails opened during this interval; the gray column
contains the cumulative total opens for all intervals to that point.
These values count all opens of the email.

Unique Clicked Number of emails clicked during this interval; the gray column
contains the cumulative total of clicks for all intervals to that point.
These values count only one click per email.

Clicked Number of email clicks during this interval; the gray column
contains the cumulative total of clicks for all intervals to that point.
These values count all clicks in the email.

Unsubscribes Number of unsubscribes from the email during this interval; the
gray column contains the cumulative total of unsubscribes for all
intervals to that point.

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

32
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Send Classification by Email Tracking

This report shows the send performance data of transactional and commercial sends. Use this report when you want to compare the
send performance data of transactional and commercial sends.

Field Name Description

Send Classification Indicates whether the send was transactional or commercial

Email Name Name of the email sent to this list

Sent Total number of emails sent during this interval

% of Send Percentage of total emails sent

Opens Number of emails opened during this interval

Open Rate Percentage of emails opened during the interval you defined; this
number is calculated by dividing the Unique Opens by Implicit
Deliveries.

Clicks Total number of email clicks during this interval

Click Rate Percentage of clicks received over the number of subscribers sent
to. This number is calculated by dividing The Unique Clicks by the
Implicit Deliveries.

Bounces Total number of emails bounced during this interval

Bounce Rates Percentage of emails sent that bounced during the interval you
defined

Unsubs Number of emails included in the send that resulted in unsubscribes

Unsub Rates Percentage of subscribers who unsubscribed as compared to

people who did not during the interval you defined. This number
is calculated by dividing Unique Unsubscribes by Implicit Deliveries.

Shares Total number of shares the send received

Delivered Number of successfully delivered emails included in this list

Delivery Rate Percentage of messages delivered

Conversions Number of conversions received during the interval you defined

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Single Email Performance by Device

The Single Email Performance by Device report displays email performance on mobile devices versus desktop devices.

33
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field name Description

Send Date Date of the email send

Sent Number of emails sent

Desktop Opens Number of times the email was opened on a desktop device

Mobile Opens Number of times the email was opened on a mobile device

Desktop Unique Opens Number of unique subscribers who opened the email on a desktop
device

Mobile Unique Opens Number of unique subscribers who opened the email on a mobile
device

Desktop Clicks Number of clicks an email link received from a desktop device.
Multiple clicks from the same subscriber are counted.

Mobile Clicks Number of clicks for an email from a mobile device. Multiple clicks
from the same subscriber are counted

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Spam Complaints Over Time

This report provides historical data on the level of spam complaints received.

Note: This is not a deliverability report and does not display the number of emails sent for domains that had no complaints
recorded. If an email domain does not return any spam complaints during the time period you specified, no entry for that domain
is shown.
The pie chart displays the top domains for spam complaints received. You can configure how many domains you want to display in the
pie chart when you run the report.
This report is divided into time intervals, with both the send and the complaint bucketed into the period during which the send occurred.

Field Name Description

Sends Number of emails sent to the ISP.

Complaints Number of spam complaints from the ISP.

Rate Percentage of emails sent that resulted in spam complaints

The report also contains thresholds used by some of the ISPs to determine when to block your emails. If your spam complaint rate is
greater than the threshold value for the ISP, the ISP could block your email sends.

Note: Values for aol.com, msn.com, hotmail.com, and yahoo.com appear in green, which indicates the bounce percentage is
within the accepted range for those domains. If the value exceeds that range, the numbers are red.

34
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Spam Complaint Bucketing

Learn how Spam Complaint Bucketing for email sends works in the Reports tool.

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Spam Complaint Bucketing

Learn how Spam Complaint Bucketing for email sends works in the Reports tool.
Your spam complaint rate is calculated by dividing the number of complaints received per day by the number of subscribers who
received your message. The spam complaint bucketing process provides a more accurate view of spam complaint rates; particularly
when displaying data breakdown by day.

Example: Suppose that you send an email to 10 subscribers on Tuesday. You receive no complaints about that email on Tuesday.
However, you get one complaint on Wednesday and one on Thursday. If you look in the tracking section of the application, you
see one complaint recorded for Wednesday and one for Thursday. However, when you run this report, you see that the two
complaints are attributed to the send on Tuesday. This works out to a 20 percent complaint rate because all complaints are bucketed
with the sends.
If the send and complaints fell into different buckets your complaint rate would be negatively impacted. In the prior example, if
you send to 10 subscribers on Tuesday and receive no complaints that day, your complaint rate for Tuesday is zero. However, with
one complaint received on Wednesday and one on Thursday, your complaint rate for those days would be greater than 100%.

Subscriber Engagement
Use this report to identify your most engaged subscribers. You could target these subscribers for special offers. This report includes the
number of emails that you have sent each subscriber over a specified period, and the number of emails the subscriber has opened or
clicked.

Note: You can specify the percentage of subscribers to include in this report based on the highest click-to-sent ratio. You can
also limit the report to include only subscribers to whom you have sent a minimum number of emails.

Field Name Description

Email Address Subscriber's email address

Delivered Number of emails sent to the subscriber over the time period of
the report

Clicked On Number of the Delivered emails in which the subscriber clicked a

link, regardless of whether the click occurred over the time period
of the report

Clicked to Delivered Ratio Percentage of Delivered emails Clicked On

Opened Number of Delivered emails the subscriber opened, regardless of

whether the open occurred over the time period of the report

35
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Description

Opened to Delivered Ratio Percentage of Delivered emails that were Opened

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Subscriber Most Recent Activity

The Subscriber Most Recent Activity report shows when each subscriber last opened or clicked a message.

Field Name Description

Email Address Subscriber's email address

Last Open Time Date and time the subscriber last opened an email from you

Last Click Time Date and time the subscriber last clicked in an email from you

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Subscribers Not Sent To

This report shows a list of emails for subscribers who weren’t included in a send during a time frame that you select.
You can use the results from this report to create a list to send a message to subscribers who weren’t included in your group sends. For
example, this report can be used to identify subscribers and resend to them if their address had a soft bounce. Soft bounces are due to
a temporary condition, such as a full inbox.

SEE ALSO:
Email Studio Reports in Analytics Builder
Bounce Mail Management in Email Studio
Create a Standard Report in Analytics Builder

Triggered Sends Tracking

The Triggered Sends Tracking report contains standard tracking information for a triggered send over a time period. You can use this
report to determine the effectiveness of a triggered send in producing opens and clicks and not causing unsubscribes.

Field Name Description

Period Window of time in which a send was triggered

Sends Number of sends triggered during the period

Deliveries Number of sends triggered during the Period that did not bounce

36
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Description

Delivery Rate Percentage of sends triggered during the Period that did not
bounce

Total Bounces Number of sends triggered during the Period that bounced

Bounce Rate Percentage of sends triggered during the Period that bounced

Unique Opens Number of sends triggered during the Period that were opened;
includes only the first time the email was opened

Open Rate Percentage of sends triggered during the Period that were opened

Cumulative Opens Total number of opens for sends triggered during the period;
includes multiple opens from the same subscriber

Unique Clicks Number of sends triggered during the Period that were clicked;
includes only the first time the email was clicked

Click Rate Percentage of the sends triggered during the Period that were
clicked

Cumulative Click Total number of clicks for sends triggered during the period;
includes multiple clicks from the same subscriber

Unique Unsubscribes Number of sends triggered during the Period that resulted in an
unsubscribe; includes only the first instance of unsubscribe

Unsubscribe Rate Percentage of the sends triggered during the Period resulting in
an unsubscribe

Cumulative Unsubscribe Total number of unsubscribes from sends triggered during the
period; includes unsubscribes through multiple channels for the
same subscriber.
For example, if a subscriber both clicks the one-click unsubscribe
link and sends a spam complaint, this value counts two
unsubscribes for the triggered send.

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Unengaged Subscribers for a List

This report shows a list of your most inactive subscribers. Use this information to target certain lists or subscribers or to clean up your
lists.
Consider removing subscribers that appear in this report or at least asking them if they'd still like to receive your email communications.

Note: The report could take several minutes to render. The report stops running if it has been active for more than three hours.

37
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field name Description

Email Address Subscriber's email address.

Delivered Number of email sends Marketing Cloud has delivered to the

subscriber.

Opens Number of email sends that subscriber has opened.

Clicks Number of clicks that subscriber has performed after opening

emails.

Note: This report includes all the statistics for the subscribers on the list, regardless of whether the information resulted from a
send to this list. If a subscriber is on two lists, the tracking for both lists appears on this report, even though you specify only one
list in this report.

SEE ALSO:
Email Studio Reports in Analytics Builder
Create a Standard Report in Analytics Builder

Journey Builder Reports

View a list and description of Journey Builder reports available in the Reports tool.

Report Name Description

Journey Builder Email Send Summary Tracking and engagement metrics for emails sent in journeys over
a specified time frame. Choose specific journeys and versions to
include in the report.

Journey Builder Email Send Summary by Day Tracking and engagement metrics for emails sent in journeys,
aggregated by day, for a specified time frame, along with specific
journeys and versions to include in the report.

Journey Builder Email Send Summary

Create this report in The Reports tool to view tracking and engagement metrics for emails sent in journeys over a specified time
frame. Choose specific journeys and versions to include in the report.
Journey Builder Email Sends by Day
Create the Journey Builder Email Sends by Day report in the Reports tool. View tracking and engagement metrics for emails sent in
journeys, aggregated by day, for a specified time frame, along with specific journeys and versions to include in the report.

SEE ALSO:
Journeys and Messages

38
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Journey Builder Email Send Summary

Create this report in The Reports tool to view tracking and engagement metrics for emails sent in journeys over a specified time frame.
Choose specific journeys and versions to include in the report.

Note: This report cannot be viewed as a webpage. Select another method of delivery such as email or FTP.

1. Choose Reports in Analytics Builder.

2. Choose Journey Builder from the Report Catalog.
3. Click Create.
4. Select report parameters.
5. Click Submit.
6. Choose the delivery option.
7. Click Save.

SEE ALSO:
Journey Builder Reports
Create a Standard Report in Analytics Builder

Journey Builder Email Sends by Day

Create the Journey Builder Email Sends by Day report in the Reports tool. View tracking and engagement metrics for emails sent in
journeys, aggregated by day, for a specified time frame, along with specific journeys and versions to include in the report.

Note: This report cannot be viewed as a webpage.

1. Select Reports in Analytics Builder.

2. Select the Journey Builder from the Report Catalog.
3. Click Create.
4. Select the report parameters.
5. Click Submit.
6. Select the delivery option.
7. Click Save.

SEE ALSO:
Journey Builder Reports
Create a Standard Report in Analytics Builder

Mobile Studio Reports

View a list and description of Mobile Studio reports available in the Reports tool.

Report Name Description

GroupConnect LINE Outbound Message Provides a summary of outbound messages sent to LINE followers,
including the delivered message count.

39
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Report Name Description

GroupConnect LINE Triggered Sends Summary Shows how many people you sent a follow or response message
to.

Mobile Chat Messaging Journey Builder Activity Summary Report Displays all Journey Builder activity related to LINE message sends.

Mobile Chat Messaging Summary Report Displays all chat messaging API send activities for LINE and
Facebook Messenger.

Push Account Summary Displays an account summary of MobilePush messages.

Push Message Detailed Report Displays detailed tracking information for all push messages sent
from a MobilePush account including message description and
individual-level send status.

Push Message Summary Provides content and overall tracking information for all push
messages sent through a specific app.

SMS Account Summary Displays a summary of activity at an account level; including a total
number of opted-in subscribers and counts of inbound and
outbound messages.

SMS Message Detailed Report Shows the detailed tracking information about messages sent,
including descriptive information about the message and send
status at an individual level.

SMS Message Summary Shows the activity summaries for all keywords in an account,
including overall tracking information and message content for
each keyword.

GroupConnect LINE Outbound Message

View the success of a list send in the LINE Outbound Message report in the Reports tool. This report displays a summary of outbound
messages sent to LINE followers, including the delivered message count. Select a date range, whether to include child accounts,
GroupConnect LINE Triggered Sends Summary
View how many people you sent a follow or response message to in the LINE Triggered Sends Summary report in the Reports tool.
Select a date range, whether to include child accounts, the time zone, and the culture code.
Mobile Chat Messaging Journey Builder Activity Summary Report
View your LINE Journey Builder message sends report using this report available in the Reports tool. This report displays LINE message
sends created in Journey Builder using a LINE activity. You can see your message type and name, audience size, and number of
successfully delivered messages.
Mobile Chat Messaging Summary Report
View the success of your chat messaging API message sends with this report accessible in the Reports tool. This report displays API
messages sent to LINE and Facebook Messenger followers, including the last status and message sends, errors, and error definitions.
With this report, you can filter by a date range, whether to include child accounts, final status, platform, or content type.
Push Account Summary
Learn about the information presented in the MobilePush Account Summary report in the Reports tool.
Push Message Detail
Learn about the information presented in the Push Message Detail report in the Reports tool.

40
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Push Message Summary

Learn about the information included in the MobilePush Message Summary report in the Reports tool.
SMS Account Summary
The SMS Account Summary report is a summary of all activity at the account level. It includes the number of opted-in subscribers
and the number of inbound and outbound messages.
SMS Message Detail
This page describes information found in the SMS Message Detail report.
SMS Message Summary Report
The SMS Message Summary Report, in the Reports tool, provides activity summaries for keywords in an account. Also included is
overall tracking information and message content for each keyword.

GroupConnect LINE Outbound Message

View the success of a list send in the LINE Outbound Message report in the Reports tool. This report displays a summary of outbound
messages sent to LINE followers, including the delivered message count. Select a date range, whether to include child accounts,

Note: The MessageID and JobID values on the report output are useful if you contact Support about a send.

SEE ALSO:
Mobile Studio Reports
Create a Standard Report in Analytics Builder

GroupConnect LINE Triggered Sends Summary

View how many people you sent a follow or response message to in the LINE Triggered Sends Summary report in the Reports tool. Select
a date range, whether to include child accounts, the time zone, and the culture code.

Note: The MessageID and JobID values on the report output are useful if you contact Support about a send.

SEE ALSO:
Mobile Studio Reports
Messages Types in GroupConnect
Create a Standard Report in Analytics Builder

Mobile Chat Messaging Journey Builder Activity Summary Report

View your LINE Journey Builder message sends report using this report available in the Reports tool. This report displays LINE message
sends created in Journey Builder using a LINE activity. You can see your message type and name, audience size, and number of successfully
delivered messages.

Mobile Chat Messaging Summary Report

View the success of your chat messaging API message sends with this report accessible in the Reports tool. This report displays API
messages sent to LINE and Facebook Messenger followers, including the last status and message sends, errors, and error definitions.
With this report, you can filter by a date range, whether to include child accounts, final status, platform, or content type.

41
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Push Account Summary

Learn about the information presented in the MobilePush Account Summary report in the Reports tool.

Field Name Variable Definition

Contacts Opt-Out Number of contacts that have opted out
during this time period

Opt-In Number of contacts that have opted in

during this time period

Message Count by Send Type Outbound Total Number of messages sent during this time
period (same as Sent under Outbound
Message Tracking)

Scheduled Number of scheduled messages sent

Automation Number of automated messages sent

API Trigger Total number of API triggered messages

Outbound Message Tracking Sent Number of messages sent during this time
period (same as Outbound Total under
Message Count by Send Type)

Opened Percentage of messages opened

Undeliverable Percentage of messages that were

undeliverable

Message Count by Campaign Number of messages sent in each

campaign, listed by Campaign Name

Campaign Name Name of a campaign that sent messages

during this time period

Message Count by App Number of messages sent per app, listed by

App Name

App Name Name of the app that sent messages during

this time

Average Time in App Average Time In App with Push-Enabled Average amount of time spent in the app
per user who has opted in to push
notifications

Average Time in App without Push-Enabled Average amount of time spent in the app
per user who has not opted in to push
notifications

SEE ALSO:
Mobile Studio Reports
Create a Standard Report in Analytics Builder

42
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Push Message Detail

Learn about the information presented in the Push Message Detail report in the Reports tool.

Field Name Description

Date Date the report was run

ClientID Business Unit ID or Member ID number for the sent message

EID Enterprise ID number for the sent message

AppName Name of the mobile app message was sent to; configured in
MobilePush Administration

MessageName Name of the sent message.

This field is populated by the name of the Push Activity in Journey
Builder.

MessageID ID number of the sent message

Template Template of the sent message: Outbound, Location Entry, Location

Exit, or Beacon

Format Format of the sent message: Application Alert or Application Alert

& Landing Page

GeofenceName Names of all geofence locations associated with the message

PageName Subject field of the cloud page that is associated with the message

Campaigns Name of the campaign associated with the sent message

DeviceID ID of the device that received the message. The Device ID is a

unique identifier assigned to a specific mobile device owned by a
contact.

ContactKey ID of the contact that owns the device that received the message
but not the ID of the device; one contact could have multiple
devices. The ContactKey matches the Contacts and Devices ID. The
ContactKey indicates the subscriber associated with the device
when the report is run.

DateTimeSend Date and time, in UTC-6, that the message was sent

MessageContent Content of the message. This field shows AMPscript, if used.

MessageOpened Whether the message was opened on the device corresponding

to the Device ID

OpenDate When the message was opened

TimeInApp How many seconds the user spent in the app after opening the
message. Measured from the time the subscriber opens the app
to the time the app goes into the background.

Platform Operating system of the device

43
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Description

PlatformVersion Version of the operating system

Status Status of the send job at the device level. This field tells you whether
the job succeeded or failed for the device.
Expected values are Success, Failed, and Blank only if there’s no
returned data on the send.

PushJobID ID of the job to use when troubleshooting with support

SystemToken Unique key that is used by Google or Apple to identify the device
for sending

InboxDownload Date and time the message was downloaded

InboxOpen Date and time Inbox was opened

RequestID Marketing Cloud’s unique identifier for every request

Note: For more details about error counts, visit the Google Cloud Messaging site and look for: Downstream message error response
codes.

SEE ALSO:
Mobile Studio Reports
Create a Standard Report in Analytics Builder
Contacts and Devices

Push Message Summary

Learn about the information included in the MobilePush Message Summary report in the Reports tool.

Field Name Variable Definition

App Name Name of the mobile app that the message
was sent to. Configured in MobilePush
Administration.

Message Name Name of the sent message

Message ID ID number of the sent message

Template Template of the sent message: Outbound,

Inbox, Location Entry, Location Exit, or
Beacon

Format Format of the sent message: Alert, Alert +

Inbox, or Inbox Only

Location Location where the message was triggered

44
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Variable Definition

Page Subject field of the cloud page that is
associated with the message

Campaign Campaign associated with the message

DateTime Sent Date and time, in UTC-6, that the message

was sent

Message Content of the message. This field shows

AMPscript, if used.

Title Title of the message (optional)

Subtitle Subtitle of the message (optional)

Total Sent Number of messages sent through the app

Opened Number of messages opened

Open% Percentage of messages opened

Time in App Total Time that users spent in the app after
opening the message. Displayed as
HH:MM:SS

Time in App Avg Average amount of time per user spent in

the app after opening the message.
Displayed as HH:MM:SS

Inbox Downloads Number of messages downloaded on a

device

iOS Media Sent Number of messages sent through the app

that reached an iOS device

Inbox Opens Number of messages opened on an iOS

device

Inbox Open% Percentage of messages opened on an iOS

device

Time in App Total Time that iOS users spent in the app after
opening the message. Displayed as
HH:MM:SS

Time in App Avg Average amount of time per iOS user spent
in the app after opening the message.
Displayed as HH:MM:SS

Inbox downloads Number of messages downloaded on an

iOS device

Android Media Sent Number of messages sent through the app

that reached an Android device

45
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Variable Definition

Inbox Opens Number of messages opened on an Android
device

Inbox Open% Percentage of messages opened on an

Android device

Time in App Total Time that Android users spent in the app
after opening the message. Displayed as
HH:MM:SS

Time in App Avg Average amount of time per Android user

spent in the app after opening the message.
Displayed as HH:MM:SS

Inbox downloads Number of messages downloaded on an

Android device

Message Failure Failed Number of messages that failed

Failed% Percentage of messages that failed

SEE ALSO:
Mobile Studio Reports
Create a Standard Report in Analytics Builder

SMS Account Summary

The SMS Account Summary report is a summary of all activity at the account level. It includes the number of opted-in subscribers and
the number of inbound and outbound messages.
To refine your results, provide a date range and select whether to include children accounts or charts in the report.

SEE ALSO:
Mobile Studio Reports
Create a Standard Report in Analytics Builder

SMS Message Detail

This page describes information found in the SMS Message Detail report.

Field Name Description

Date Date the message was sent

EID Enterprise ID number for the sender

ClientID Business Unit ID number for the sender

MessageName Name of the message sent

MessageType Type of message sent

46
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Field Name Description

CampaignName Name of the campaign associated with the message sent

MessageOrigin Origin of the sent message

MessageText Text included in the message sent

MobileNumber Mobile number associated with the sender

IsoCountryCode ISO country code of the message sent

ShortCode Short-code associated with the sent message

Status Status of the sent message. The message is either Delivered or

Undelivered.

MobileMessageTrackingID Unique ID for tracking information related to the sent message

SubscriberKey Unique ID for the subscriber

SEE ALSO:
Mobile Studio Reports
Create a Standard Report in Analytics Builder

SMS Message Summary Report

The SMS Message Summary Report, in the Reports tool, provides activity summaries for keywords in an account. Also included is overall
tracking information and message content for each keyword.

Note: SMS messages created in Content Builder only show in the SMS Message Detail report.

Enter a date range and select whether to include children accounts in the report.

Field Name Description

MessageName Name of the message sent

MessageType Type of message sent

CampaignName Name of the campaign associated with the message sent

MessageOrigin Origin of the sent message

ShortCode Short-code associated with the sent message

SEE ALSO:
Mobile Studio Reports
Create a Standard Report in Analytics Builder

Marketing Cloud Analytics Builder Reports Frequently Asked Questions

Get the answers to frequently asked questions about the standard reports in Marketing Cloud Analytics Builder.

47
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

How Do I Access Marketing Cloud Analytics Builder Reports?

Navigate to Analytics Builder and select Reports from the dropdown.
What Type of Security is Applied to the Reports Tool?
Reports have a permission model that an administrator can control. Initially, all users that have access to the Marketing Cloud has
access to all eligible reports for an account. Eligible reports for an account are determined based on what channel applications are
provisioned. For example, if Email Studio is enabledbut MobileConnect and Social Studio aren’t enabled, then the user would only
have access to Email Studio reports.
Can Reports Be Scheduled?
Yes, all standard Marketing Cloud Analytics Builder reports can be scheduled to run at specified dates and times.
Can I Create Custom Reports in Analytics Builder?
To create custom reports in Marketing Cloud Analytics Builder, enable the Discover reporting tool first on your account. Contact your
account executive for more information.
Can a Report Owner Give Read/Write Access to Others for Report they've created and saved?
No. You can’t share permissions for a report created within Analytics Builder. However, a different user can access a report and
perform a Save As to create a copy. Report ownership can’t be transferred from one user to another.
Does Marketing Cloud Analytics Builder Reporting Include Reports for All Channels?
Yes, all reports available in each channel are accessible from the Reports Catalog.
Do I Have to Set Permissions to Access Reports I have Email Studio?
Yes, you must set permissions in Reports for each user.
What Languages are Supported?
Reports are available in all languages supported by Marketing Cloud.
Are There Changes to the External APIs?
There are no changes to the external APIs.
What Email Editions are Supported?
All email editions have access to Marketing Cloud Analytics Builder Reports.
Can I Save a Report?
Yes, you can save, retrieve, and rerun reports in Marketing Cloud Analytics Builder.
Can I Search for A Specific Report?
Yes. In Marketing Cloud Analytics Builder Reports, use the search by name tool or use filters to locate a specific report.
Are Marketing Cloud Analytics Builder Reports Available for All Email Editions?
Yes, standard reports are available for all Email Studio editions.

How Do I Access Marketing Cloud Analytics Builder Reports?

Navigate to Analytics Builder and select Reports from the dropdown.

What Type of Security is Applied to the Reports Tool?

Reports have a permission model that an administrator can control. Initially, all users that have access to the Marketing Cloud has access
to all eligible reports for an account. Eligible reports for an account are determined based on what channel applications are provisioned.
For example, if Email Studio is enabledbut MobileConnect and Social Studio aren’t enabled, then the user would only have access to
Email Studio reports.

48
Marketing Cloud Einstein and Analytics Standard Reports for Marketing Cloud Data Management
and Analytics

Can Reports Be Scheduled?

Yes, all standard Marketing Cloud Analytics Builder reports can be scheduled to run at specified dates and times.

Example: After a report is saved, click the schedule icon.

Scheduling options include start date and time, time zone, and the options to run once, hourly, daily, weekdays, weekly, or monthly.
Delivery options include file format and the delivery location.

Example:

Note: If you configure the report with an end date past 2078, an internal error occurs and the scheduled date doesn’t save.

Can I Create Custom Reports in Analytics Builder?

To create custom reports in Marketing Cloud Analytics Builder, enable the Discover reporting tool first on your account. Contact your
account executive for more information.

Can a Report Owner Give Read/Write Access to Others for Report they've created and saved?
No. You can’t share permissions for a report created within Analytics Builder. However, a different user can access a report and perform
a Save As to create a copy. Report ownership can’t be transferred from one user to another.

Does Marketing Cloud Analytics Builder Reporting Include Reports for All Channels?
Yes, all reports available in each channel are accessible from the Reports Catalog.

Do I Have to Set Permissions to Access Reports I have Email Studio?

Yes, you must set permissions in Reports for each user.

What Languages are Supported?

Reports are available in all languages supported by Marketing Cloud.

SEE ALSO:
Marketing Cloud Account Culture Code

Are There Changes to the External APIs?

There are no changes to the external APIs.

What Email Editions are Supported?

All email editions have access to Marketing Cloud Analytics Builder Reports.

49
Marketing Cloud Einstein and Analytics Collect Tracking Code

Can I Save a Report?

Yes, you can save, retrieve, and rerun reports in Marketing Cloud Analytics Builder.

Can I Search for A Specific Report?

Yes. In Marketing Cloud Analytics Builder Reports, use the search by name tool or use filters to locate a specific report.

Are Marketing Cloud Analytics Builder Reports Available for All Email Editions?
Yes, standard reports are available for all Email Studio editions.

Collect Tracking Code

Collect Tracking Code is a JavaScript snippet you can use to capture data about known contacts and unknown visitor behavior. You can
use this data to enhance Contact profiles and optimize customer journeys across channels through predictive and personalized
recommendations. You can also update product and content catalog details in real time or to track email-driven revenue.
When a visitor hits your website with the Collect code installed, a cookie is dropped with a unique ID and session ID. The cookie
automatically adds an ID to all Collect Calls. The cookie tracks the user until it is removed or cleared.
Collect Tracking Code monitors the variables and events you select at the contact level including:
• Browser type

• User location

• Session time and length

• Page URL

• Page title

• Referrer URL

Configurations vary by product and use case.

Note: The Collect Tracking Code pixel identifies itself as an invisible image and does not affect the user experience of website
visitors who use a screen reader.
Considerations:
• All Collect calls associated with items, such as Track Item Detail, Track Cart, and Track Purchase, must match a value in the Catalog.
Items not matching in the Catalog is one of the top implementation problems. The Status tab in the Marketing Cloud Email or Web
Recommendations application provides insight into whether Collect data matches catalog data.
• Collect calls cannot pass more data about the page that you are viewing, nor can the name-value pairs in the calls be changed.
Values like item, unique_id, and email are fixed labels. Never replace fixed labels with custom labels.

Install Collect Tracking Code

Install Collect Tracking Code on your website.
Streaming Catalog Updates Through Collect Tracking Code
To configure server-side streaming updates for single or multiple items in your catalog, use the API key or catalog import option.
Streaming updates replaces the standard file upload process.

50
Marketing Cloud Einstein and Analytics Install Collect Tracking Code

Set Contact Attribute Affinity

Use Collect Tracking Code to build subscriber affinity models based on contact attributes.
Set User Info and Attributes in Collect Tracking Code
Configure Marketing Cloud Collect Tracking Code to create and maintain a basic user record and add optional subscriber information
to a contact profile.
Track Category Viewed
Configure Collect Tracking Code to store category data for the product a contact views on your website.
Track In-Site Search
Configure Collect Tracking Code to store data about a contact’s search on your website.
Track Items in Cart
Configure Collect Tracking Code to track items added or removed from a contact's cart.
Track Page View
The trackPageview call is the most common call and can capture three types of information: product or content views, categories
views, or search views. No data outside of the item, category, and search name: value pair can be passed in the trackPageview call.
Track Purchase Details
Configure Collect Tracking Code to store details about a contact’s purchases from your website.
Track User Rating
Configure Collect Tracking Code to store contact ratings for items on your website.
Configure trackWishlist for Behavioral Triggers and Collect Tracking Code
In Marketing Cloud Behavioral Triggers and Collect Tracking Code, you must use trackWishlist for Abandoned Wishlist emails. Configure
Collect Tracking Code to store contact wishlists for items on your website. We recommend that you consult your web developer to
complete the installation and configuration of Collect Tracking Code.

SEE ALSO:
Install Collect Tracking Code

Install Collect Tracking Code

Install Collect Tracking Code on your website.
To begin configuration of Collect Tracking Code, select Email Recommendations or Web Recommendations under Personalization
Builder in the app switcher. Select Collect and complete the steps. Then install Collect Tracking Code on your site.

Note: We recommend that you consult your web developer to complete the installation and configuration of Collect Tracking
Code.
1. Copy and paste your Collect Script within the <head> or <body> in your website template. This step automatically installs the
code on every page of the website. Replace MID with your business unit account ID.
Collect Code Script
<script type="text/javascript" src="https://MID.collect.igodigital.com/collect.js">
</script>

2. Copy and paste the Set Org ID Script between the body tags of each page of your website. Replace MID with your business unit
account ID.

51
Marketing Cloud Einstein and Analytics Install Collect Tracking Code

Set Org ID Script

<script type="text/javascript">
_etmc.push(["setOrgId", "MID"]);
_etmc.push(["trackPageView"]);
</script>

Tip: Use Options and Configuration within Personalization Builder to modify predictive recommendations features. Changes
made in Personalization Builder take effect immediately.

Note: To enable subscribers to opt out of tracking on your website, replace the Set Org ID Script with Do Not Track Script on
page 52.

Do Not Track Script

Use Do Not Track Script code to suppress Collect Tracking Code on your website when a subscriber opts out of tracking. Collect
Tracking Code doesn’t use browser settings to determine whether to track user activity.
Configure Collect Tracking Code for Personalization Builder
Configure Collect Tracking Code for use with Personalization Builder.

SEE ALSO:
Do Not Track Script

Do Not Track Script

Use Do Not Track Script code to suppress Collect Tracking Code on your website when a subscriber opts out of tracking. Collect Tracking
Code doesn’t use browser settings to determine whether to track user activity.
This code suppresses all tracking activities, including:
• trackCart
• trackConversion
• trackEvent
• trackPageView
• trackRating
Use this code in place of the standard Set Org ID script:
<script type="text/javascript">
_etmc.push(["setOrgId", "123456"]);
_etmc.push(["doNotTrack"]);
_etmc.push(["trackPageView"]);
</script>

To manage privacy settings through API, visit Personalization Builder API developer documentation.

SEE ALSO:
Configure Collect Tracking Code for Personalization Builder
Consent Management for Marketing Cloud
Data Deletion for Marketing Cloud

52
Marketing Cloud Einstein and Analytics Streaming Catalog Updates Through Collect Tracking Code

Configure Collect Tracking Code for Personalization Builder

Configure Collect Tracking Code for use with Personalization Builder.
1. Go to Personalization Builder and select Web Recommendations or Email Recommendations.
2. Hover over Admin and select Implementation from the dropdown.
3. Select your catalog sync method: Streaming Updates or Batch Upload.
• For streaming updates, provide a domain name and select the catalog type
• For batch upload, provide information required for manual catalog upload and update

4. Select the attributes you want to track and copy and paste codes for all attributes to track.

SEE ALSO:
Set User Info and Attributes in Collect Tracking Code
Streaming Catalog Updates Through Collect Tracking Code

Streaming Catalog Updates Through Collect Tracking Code

To configure server-side streaming updates for single or multiple items in your catalog, use the API key or catalog import option. Streaming
updates replaces the standard file upload process.

Important: Streaming updates via Client-Side JavaScript is no longer supported.

To remove an item from the pool of recommendable items, use the API.
• Requests to the server-side streaming updates service via HTTP aren’t accepted. Instead, use HTTPS in all requests to the streaming
update service.
• API keys sent as URI query parameters aren’t accepted. Instead, move the API key into the body of the request.
In these examples, replace MID with the account ID of the business unit used for Collect Tracking Code.
Updating a single item
https://MID.collect.igodigital.com/c2/MID/update_item_secure.json
{
"api_key": "a1234567-cccc-1234-a123-12345a123456",
"payload": {
"item": "INSERT_ITEM",
"unique_id": "INSERT_UNIQUE_ITEM_ID",
"item_type": "INSERT_ITEM_TYPE",
"name": "INSERT_ITEM_NAME_OR_TITLE",
"url" : "INSERT_ITEM_URL",
"INSERT_ATTRIBUTE_NAME": "INSERT_ATTRIBUTE_VALUE"
}
}

Updating multiple items

https://MID.collect.igodigital.com/c2/MID/update_item_secure.json
{
"api_key": "a1234567-cccc-1234-a123-12345a123456",
"payload": {
"item": "INSERT_ITEM",

53
Marketing Cloud Einstein and Analytics Set Contact Attribute Affinity

"unique_id": "INSERT_UNIQUE_ITEM_ID",
"name": "INSERT_ITEM_NAME_OR_TITLE",
"url": "INSERT_ITEM_URL",
"item_type": "INSERT_ITEM_TYPE",
"INSERT_ATTRIBUTE_NAME": "INSERT_ATTRIBUTE_VALUE"
},
{
"item": "INSERT_ITEM",
"unique_id": "INSERT_UNIQUE_ITEM_ID",
"name": "INSERT_ITEM_NAME_OR_TITLE",
"url": "INSERT_ITEM_URL",
"item_type": "INSERT_ITEM_TYPE",
"INSERT_ATTRIBUTE_NAME": "INSERT_ATTRIBUTE_VALUE"

}
}

SEE ALSO:
Install Collect Tracking Code
Einstein Recommendations Prerequisites
Install Collect Tracking Code

Set Contact Attribute Affinity

Use Collect Tracking Code to build subscriber affinity models based on contact attributes.
Match a contact attribute to a tagged catalog field to increase the subscriber's affinity for the value of that contact attribute. The amount
of increase is less than what results from a purchase but more than the increase from a view.
<script type="text/javascript">
_etmc.push(["setOrgId", "MID"]);
_etmc.push(["setUserInfo", {"email": "INSERT_EMAIL_OR_UNIQUE_ID",
"details": {
"gender: "female"
}
}]);
_etmc.push(["trackPageView"]);
</script>

1. Copy the script and replace gender with the contact attribute you want to match.
2. Add the modified script in the header code on the detail pages of your website.

Example: Lisa’s marketing director wants to increase the user affinity for catalog items where the gender field value is female
for customers who identify as female. Lisa uses the Set Contact Attribute Affinity code to permanently boost any item that has the
value female in the gender field.

SEE ALSO:
Install Collect Tracking Code
Catalog
Configure Custom Attributes

54
Marketing Cloud Einstein and Analytics Set User Info and Attributes in Collect Tracking Code

User Affinity Tag Scenario

Configure a tag scenario to return the most popular items with a particular catalog attribute value. Set the recommendation engine to
return items with attribute values that match the top affinities of a contact. This feature can power recommendations like Brands You
Love or Items in your Favorite Colors.
1. Highlight the catalog attribute to use.
2. Select Same as User Affinity as the value.

Example: Lisa’s marketing director wants to increase the user affinity for catalog items where the gender field value is female
for customers who identify as female. Lisa uses the Set Contact Attribute Affinity code to permanently boost any item that has the
value female in the gender field.
The SetUserInfo call can also include customer attributes specific to the contact on the site. The label can be any value and pulls
into the Contact Profile exactly as passed. The value for each pair overwrites any value that is on the profile for the active user.
To use the affinity seeding functionality, the label must match the field in the catalog and the value passed must be assigned to
a product on the catalog.
Customer Attributes cannot be exported and currently do not get passed into Marketing Cloud data extensions. The primary use
cases for these values are to seed Contact Attribute Affinity and to use these values in rules in influence recommendations. For
example, a financial institution adds AgeGroup as Minor for some users, and then creates a rule that prohibits the recommendation
engine from recommending items whereOfferType=CreditCard when AgeGroup = Minor.

Set User Info and Attributes in Collect Tracking Code

Configure Marketing Cloud Collect Tracking Code to create and maintain a basic user record and add optional subscriber information
to a contact profile.
The setUserInfo push is an important addition to the call by passing the Contact ID. No matter what type of ID is chosen, use the email
label for this field and add the value in the SetUserInfo snippet. You do not need to add it to every page because adding it once ties the
known identifier to the Collect Tracking Code cookie.

Tip: Configure Collect Tracking Code to store subscriber information when a contact enters an email address on the website or
clicks through a marketing email. In order to use the Personalization Builder Integrations on page 338, you must use the user's
email address. For privacy reasons, we recommend using a non personally identifiable information (PII) identifier or hashing the
email.
Set User Info
<script type="text/javascript">
_etmc.push(["setOrgId", "MID"]);
_etmc.push(["setUserInfo", {"email": "INSERT_EMAIL_OR_UNIQUE_ID"}]);
_etmc.push(["trackPageView"]);
</script>

Tip: Add this call everywhere that a user logs in or becomes known. Some common areas to be watching for include:
• login pages or modals
• signup pages or modals
• login steps, check out process, and so forth
• newsletter signup

1. Copy and customize the script by replacing "INSERT_EMAIL_OR_UNIQUE_ID" with dynamic code to get the Subscriber ID. A Subscriber
ID is typically an email address or number unique to that user.

55
Marketing Cloud Einstein and Analytics Track Category Viewed

2. Add the modified script in the header code on your pages.

SEE ALSO:
Install Collect Tracking Code

Track Category Viewed

Configure Collect Tracking Code to store category data for the product a contact views on your website.
The trackpageviewcall is also used on category pages to capture the category viewed by a visitor. This call uses the category
name:value pair and the label is reserved.
The category value is flexible but we recommend that you use a consistent type of data. Our best practice is to include values that match
tag fields in the catalog. Use the same structure for all type page categorizations, from categories to subcategories to brands.
Only one category is added to the Collect call at a time, so choose the most relevant term for the page being viewed, which is usually
the most specific category. If viewing a category page with a breadcrumb of Men’s > Apparel > Shoes > Tennis Shoes, the category
would often be “Tennis Shoes” and would tie to a “Tennis Shoes” category in the product catalog.

Tip: Consistency is the key to the category call. The key is not required for a successful implementation. If you have category IDs
or category names, it needs to match a tagged value in the catalog.
<script type="text/javascript">
_etmc.push(["setOrgId", "MID"]);
_etmc.push(["trackPageView", { "category" : "INSERT_CATEGORY" }]);
</script>

1. Copy and customize the code by replacing "INSERT_CATEGORY" with dynamic code for the category of items viewed.
2. Add the modified script in the header code on your category pages.

SEE ALSO:
Install Collect Tracking Code
Track In-Site Search
Track Items in Cart
Track Page View
Track Purchase Details
Track User Rating
Validate Collect Tracking Code Implementation

Track In-Site Search

Configure Collect Tracking Code to store data about a contact’s search on your website.

Note: If not explicitly needed for a particular use-case, the Track In-Site Search call is not required for successful implementation
and is oftentimes not implemented.
<script type="text/javascript">
_etmc.push(["setOrgId", "MID"]);
_etmc.push(["trackPageView", { "search" : "INSERT_SEARCH_TERM" }]);
</script>

56
Marketing Cloud Einstein and Analytics Track Items in Cart

1. Copy the code and replace “INSERT_SEARCH_TERM” with dynamic code that pulls in the search term.
2. Paste the modified script in the header code on your detail pages.

SEE ALSO:
Install Collect Tracking Code
Track Category Viewed
Track In-Site Search
Track Items in Cart
Track Page View
Track Purchase Details
Track User Rating

Track Items in Cart

Configure Collect Tracking Code to track items added or removed from a contact's cart.
Use trackCart anytime a shopping cart changes, such as when a visitor adds or removes a product to the cart, or updates the
quantity of a product in the cart.
This code overwrites items in the contact’s cart with the newest information, including the quantity and unit price for each item. If a cart
has multiple products, each product must be added to the call each time it is captured. The active cart must be added to the call every
time. This call is critical for Abandon Cart triggers, which uses this call to determine which products to show were abandoned.
The call is made up of 4 name: value pairs, item, quantity, price, and unique_id. Item and unique_id are required.
• The quantity is the number of items added for the particular SKU.
• The price is the price at the time of adding an item to the cart.
• The item, just like in all calls, matches the field mapped to ProductCode in the catalog.
• The unique_id matches the field mapped to the SKUId in the catalog. When these items match it ensures the exact record in the
catalog, including all specific attributes like color and size, is tied to the cart rather than just the ProductCode.
Use the trackCart each time a product is added to the cart or the cart is updated. This activity often occurs on multiple places on
the site including:
• Product Pages
• Category Pages
• Quick Cart
• Cart Page
• Search Results
• Landing Pages
• Home page
Our Best Practice is to include setUserIdwith trackCart . This practice helps to ensure that the correct Contact ID is always tied
to the cart. It is not a requirement since setUserInfo only needs to be set once. However, we highly recommend adding it on all
cart calls to ensure that the correct Contact ID is tied to the cart.
Track Cart script:
<script type="text/javascript">
_etmc.push(["setOrgId", "MID"]);

57
Marketing Cloud Einstein and Analytics Track Page View

_etmc.push(["trackCart", { "cart": [
{"item" : "INSERT_ITEM", "quantity": "INSERT_QUANTITY" , "price" : "INSERT_PRICE" ,
"unique_id" : "INSERT_UNIQUE_ID" } ,
{"item" : "INSERT_ITEM", "quantity": "INSERT_QUANTITY" , "price" : "INSERT_PRICE" ,
"unique_id" : "INSERT_UNIQUE_ID" }
]}]);
</script>

1. Copy and customize the script.

2. Add the modified script in the header code on your detail pages.

SEE ALSO:
Install Collect Tracking Code
Track Category Viewed
Track In-Site Search
Track Page View
Track Purchase Details
Track User Rating

Clear Cart
Use this code to clear all items from a contact’s cart when the contact manually removes all items from the cart.
This call is vital for implementations with Abandon Cart triggers, as contact receive unwanted abandon cart emails for products they
cleared from their cart.
<script type="text/javascript">
_etmc.push(["setOrgId", "MID"]);
_etmc.push(["trackCart", { "clear_cart": true } ]);
</script>

Note: The trackConversion method clears the contact cart automatically.

Track Page View

The trackPageview call is the most common call and can capture three types of information: product or content views, categories views,
or search views. No data outside of the item, category, and search name: value pair can be passed in the trackPageview call.
<script type="text/javascript">
_etmc.push(["setOrgId", "MID"]);
_etmc.push(["trackPageView", { "item" : "INSERT_PRODUCT_CODE","search" : "XXXXX" }]);

</script>

Note: To have the search field populated in IGO_VIEWS, include the search parameter in the tracking call. Use the item parameter
to create a record in IGO_VIEWS.
1. Copy the script and replace INSERT_PRODUCT_CODE with the attribute you want to match.

58
Marketing Cloud Einstein and Analytics Track Purchase Details

2. Paste the modified script in the header code on your detail pages.

SEE ALSO:
Install Collect Tracking Code
Track Category Viewed
Track In-Site Search
Track Items in Cart
Track Purchase Details
Track User Rating

Track Purchase Details

Configure Collect Tracking Code to store details about a contact’s purchases from your website.
There are two methods for tracking purchase details available in the Marketing Cloud. Track Conversion through Collect Tracking Code
is most often used. Alternatively, use an AJAX Reconnector Call to track the same information.

SEE ALSO:
Install Collect Tracking Code
Track Category Viewed
Track In-Site Search
Track Items in Cart
Track Page View
Track User Rating

Track Conversion
<script type="text/javascript">
_etmc.push(["setOrgId", "MID"]);
_etmc.push(["trackConversion", { "cart": [
{"item" : "INSERT_ITEM", "quantity": "INSERT_QUANTITY" , "price" : "INSERT_PRICE" ,
"unique_id" : "INSERT_UNIQUE_ID" } ,
{"item" : "INSERT_ITEM", "quantity": "INSERT_QUANTITY" , "price" : "INSERT_PRICE" ,
"unique_id" : "INSERT_UNIQUE_ID" }],
// OPTIONAL PARAMETERS
"order_number" : "INSERT_ORDER_NUMBER",
"discount" : "INSERT_DISCOUNT",
"shipping" : "INSERT_SHIPPING",
"details" : { "AttributeName" : "Value" }
// END OPTIONAL PARAMETERS
}]);
</script>

1. Copy and customize the Track Conversion script to include the attributes to track.
2. Paste the modified script in the header code on your detail pages. This method requires the same structure as the Track Cart script.
3. Optionally, add order level information including:
• Order number

59
Marketing Cloud Einstein and Analytics Track Purchase Details

• Shipping charges

• Discounts applied

• Custom details

Example: Example
If Lisa sets conversion tracking as follows:
_etmc.push(["trackConversion", { "cart": [ {"item" : "123", "quantity": "2" ,
"price" : "10.00" , "unique_id" : "123" } , {"item" : "234", "quantity": "1" ,
"price" : "5.00" , "unique_id" : "234" } ],
// OPTIONAL PARAMETERS
"order_number": "123456",
"discount": "2.00",
"shipping": "5.00"
// END OPTIONAL PARAMETERS
}]);
The resulting values stored in the data extension are:
SKU price quantity order_number
123 11.2 2 123456
234 5.6 1 123456
The formula used to calculate price is:
price + ((shipping - discount) * $ percentage of order/quantity)
For SKU 123, which accounts for 80% of the $25 order, it looks like: 10 + ((5-2) *.8/2) = 10 + (3 * .4) = 11.20

AJAX Redirector Call

Use an AJAX call to track order detail information not available on your confirmation screen.

Example:
<html><a href="http://ntoutfitters.com/product/4064100"
onclick="igoClickTracker('http://stack9.collect.igodigital.com/redirect/v2eyJuIVsbGVyc1JlZ2lvbiIsInUiOiI0MDkzMzQyNiIsInIiOjUxNDUsInB...=')">Crestone
75 Pack</a>
<script type="text/javascript">
function igoClickTracker(click_url) {
var xmlhttp;
if (window.XMLHttpRequest) {
// code for IE7+, Firefox, Chrome, Opera, Safari
xmlhttp = new XMLHttpRequest();
} else {
// code for IE6, IE5
xmlhttp = new ActiveXObject("Microsoft.XMLHTTP");
}

xmlhttp.open("POST", click_url , true);

60
Marketing Cloud Einstein and Analytics Track User Rating

xmlhttp.send();
}
</script>

Track User Rating

Configure Collect Tracking Code to store contact ratings for items on your website.
<script type="text/javascript">
_etmc.push(["setOrgId", "MID"]);
_etmc.push(["trackRating", { "rating" : 5,
"item" : "INSERT_ITEM",
"unique_id" : "INSERT_UNIQUE_ID" }]);
</script>

Note: Match the value sent for "INSERT_ITEM" to the Product Code catalog field if you include a catalog file with your Personalization
Builder implementation.
1. Copy and customize the script by replacing "INSERT_ITEM" with dynamic code for the unique identifier of the item rated. Optionally,
replace "INSERT_UNIQUE_ID" with the dynamic code to pull in the unique child identifier for the item rated.
2. Paste the modified script in the header code on your detail pages.

SEE ALSO:
Install Collect Tracking Code
Track Category Viewed
Track In-Site Search
Track Items in Cart
Track Page View
Track Purchase Details

Configure trackWishlist for Behavioral Triggers and Collect Tracking Code

In Marketing Cloud Behavioral Triggers and Collect Tracking Code, you must use trackWishlist for Abandoned Wishlist emails. Configure
Collect Tracking Code to store contact wishlists for items on your website. We recommend that you consult your web developer to
complete the installation and configuration of Collect Tracking Code.
1. Copy the script.
<script type="text/javascript">
_etmc.push(["setOrgId", "MID"]);
_etmc.push(["trackWishlist", {
"items" : ["INSERT_ITEM_1", "INSERT_ITEM_2", "INSERT_ITEM_3"],
"skus" : ["INSERT_UNIQUE_ID_1", "INSERT_UNIQUE_ID_2", "INSERT_UNIQUE_ID_3"
</script>

Note: Match the value sent for "INSERT_ITEM" to the Product Code catalog field if you include a catalog file with your
Personalization Builder implementation. Each subsequent trackWishlist call replaces the contact’s wishlist data. If you want
their entire wishlist to persist, include all items in each call.

2. To customize it, replace "INSERT_ITEM_X" with dynamic code for the unique identifier of the item rated.

61
Marketing Cloud Einstein and Analytics Validate Collect Tracking Code Implementation

3. To pull in the unique child identifier for the item rated, you can replace "INSERT_UNIQUE_ID" with the dynamic code.
4. Paste the modified script in the header code on the pages where users manage their wishlist.

Validate Collect Tracking Code Implementation

View the Installation Status console to confirm that your Collect Tracking Code implementation is successful.
To access the Installation Status console, click the Status tab inside Personalization Builder. Current statistics from this tracking system
are used to optimize performance on the site.

Tip: Go to your site in the same browser to view a product, add it to a cart, and make a purchase before you attempt to validate
the code. If your site has an email intake field, enter an email address.
After configuring a catalog, and deploying Collect Tracking Code to your website, proper installation of Collect Tracking Code is essential
for all Personalization Builder use cases.
1. Browse your website, ensuring that you visit each class of page on which you’ve installed Collect Tracking Code. For example, visit
the home page, navigate to a product detail page, add it to your cart, and purchase it.
2. Log in. Select Email Recommendations or Web Recommendations under Personalization Builder.
3. Click the Status Tab.
4. The Status Console provides a lens into today’s traffic on each class of page. Ensure that the counts for each type of page have
incremented as you expect them.
5. The Status Console also shows common implementation problems and provides details on how to fix them.
6. You can subscribe to notifications to receive an email if data collection stops on a particular class of page. The notification alerts you
when Collect Tracking Code is broken on a page.

Intelligence Reports for Engagement

Intelligence Reports for Engagement enables you to generate, view, and share a detailed analysis
EDITIONS
of your Email, Push, and Journey campaign-level data. Intelligence Reports for Engagement
Advanced, a premium upgrade of Intelligence Reports, adds more features, functionality, and Available in: Intelligence
analytics. The Advanced upgrade is available at an additional cost. Reports for Engagement and
Intelligence Reports for Engagement is powered by Marketing Cloud Intelligence, and is available Intelligence Reports for
in two versions: Engagement Advanced

• Intelligence Reports for Engagement—This standard version is included in Pro editions and
higher. Intelligence Reports for Engagement includes dashboards, pivot tables and reports.
With Intelligence Reports for Engagement, you can:
– Analyze your data, and then receive intuitive analytics with built-in dashboards that visualize aggregated Email, Push, and Journey
data up to the business unit level.
– View comparisons, trends, and patterns in your data, and organize and summarize data in a custom report.
– Filter, sort, and summarize data with pivot tables, and share findings with scheduled reports.
– Manipulate, visualize, and share pivot tables, dashboards, and scheduled reports.

• Intelligence Reports for Engagement Advanced— This premium version is available as an add-on for Pro editions and above.
Intelligence Reports for Engagement Advanced includes more dashboard capabilities, pivot tables, reports, cross-channel apps, and
query options. Intelligence Reports for Engagement Advanced, is a premium upgrade of Intelligence Reports for Engagement that

62
Marketing Cloud Einstein and Analytics Intelligence Reports for Engagement

adds more features, functionality, and analytics. The Advanced upgrade is available at an additional cost. With Intelligence Reports
for Engagement Advanced, you can:
– Connect, visualize, and analyze key data sources quickly with out-of-the-box cross-channel apps built by Marketing Cloud
Intelligence.
– Customize and create dashboards that meet the end users’ needs.
– Create and refine your key performance indicators (KPIs).
– Create more fields and attributes using Marketing Cloud Intelligence’s 100+ functions.

Here’s a comparison between the two different versions:

Feature Intelligence Reports Intelligence Reports Advanced

View built-in dashboards

Create and manage reports

Create and manage pivot tables

Create and customize dashboards

Create and manage calculated

measurements and dimensions

Query granular data

View and install cross-channel apps

Connect and query data extensions

The Intelligence Reports and Intelligence Reports Advanced interface support five languages: English, Japanese, German, French, and
Spanish.

Note:
• Some of the screens haven’t been translated yet.
• Currently dashboards aren’t translated.
• Dimension and measurement names appear in English.
• All dimension and measurement values appear in their source language, no matter the language. For example if your campaign
name is in Spanish, it appears as is in all reports.

Here’s a video about Intelligence Reports for Engagement:

Watch a video

For more information about Intelligence Reports for Engagement, see:

Start Learning About Intelligence Reports

If you’re a new user or need a refresher, click on the learning maps below to learn the basics of Intelligence Reports and Intelligence
Reports Advanced. The learning maps contain links to other resources, like Trailhead and videos, and starter help topics. You can
always come back to the learning maps to refresh your skills, or check out newly added content.

63
Marketing Cloud Einstein and Analytics Intelligence Reports for Engagement

User Roles and Permissions in Intelligence Reports

To use Intelligence Reports for Engagement, your account must be assigned the Intelligence Reports for Engagement user role. The
user role has the following permissions: Access, View and Export, Schedule, and Create and Edit.
Access Intelligence Reports
To access Intelligence Reports for Engagement, you need the required user role assigned to your account. When assigning the user
role, you can also assign permissions in Intelligence Reports. For example, you can create pivot tables, but you can’t edit or save
them.
Overview of Data in Intelligence Reports
Intelligence Reports for Engagement displays both Email, Push, and Journey campaign-level data. Intelligence Reports for Engagement
doesn’t display subscriber-level data or event-level data. However, subscriber-level data can be used to generate campaign-level
analytics. With Intelligence Reports for Engagement you can see how many emails or messages were opened, delivered, and clicked.
The data that is displayed is daily aggregated metrics. For example, you can see the number of send and open rates per day, during
the last 90 days, for a specific campaign.
Dimensions and Measurements
Dimensions and measurements are included when viewing dashboards, pivot tables, and reports. Use categories to find the data
that’s most relevant to you.
Send Date Versus Event Date
All engagement events in Intelligence Reports have two date dimensions: Event, and send.
Dashboards
Dashboards provide an out-of-the box view of your Email, Push, and Journey data. With dashboards, you gain valuable insights and
can quickly identify trends or anomalies. With the premium Advanced version, you can also create and edit dashboards.
Pivot Tables Overview
Pivot tables allow you to explore your data from multiple perspectives. You can calculate, summarize, and analyze data by seeing
comparisons, patterns, and trends in your data. With pivot tables, you can create custom reports without the need for query formulas,
such as SQL queries.
Reports Overview
Reports are an easy way to retrieve, view, and share a detailed analysis of your data. You can create the report from scratch by going
to the Reports tab and clicking Create New Report. Or you can create the same report by using the Schedule Export option when in
a dashboard page or in a pivot table. For example, to create a flat table report, create the report from scratch in Excel, or go to a
predefined pivot table and use the Schedule Export Flat Table option.
Cross-Channel Apps
Cross-Channel apps allow you to take your data from separate silos, and then connect, visualize, and analyze your key data sources.
The apps are available in the Cross-Channel tab, where you can demo and install various apps.
Queries
Use Queries to pull granular data and get insights on your subscriber level data. For example, learn which subscribers engaged in a
particular journey or investigate messages sent to a specific subscriber. Explore and export results for a deeper understanding of
your data.
Calculated Fields
Create calculated fields in Intelligence Reports Advanced when you need customized dimensions and measurements.
Data Extensions
Query your engagement data with data extension data to retrieve additional attributes and measurements. Identify trends and get
marketing insights based on performance by audience attributes from your data extensions.

64
Marketing Cloud Einstein and Analytics Start Learning About Intelligence Reports

Differences Between Intelligence Reports and Other Reports

When using other Marketing Cloud reporting tools, such as Data Views, the results you see can vary depending on the type of report
and its purpose.
Set Up Intelligence Reports on Hyperforce - India Only
Configure your Data Cloud connection to support Hyperforce. Using Hyperforce requires a new connection between Data Cloud
and Marketing Cloud. Intelligence Reports provisioned for Marketing Cloud Engagement is hosted on a Salesforce-managed Hyperforce
infrastructure in the AWS India region. Intelligence Reports on Hyperforce uses data service credits on Data Cloud.

Start Learning About Intelligence Reports

If you’re a new user or need a refresher, click on the learning maps below to learn the basics of
EDITIONS
Intelligence Reports and Intelligence Reports Advanced. The learning maps contain links to other
resources, like Trailhead and videos, and starter help topics. You can always come back to the Available in: Intelligence
learning maps to refresh your skills, or check out newly added content. Reports and Intelligence
Reports Advanced
Intelligence Reports Learning Map
Learn more about Intelligence Reports by navigating through the different resources.
Intelligence Reports Advanced Learning Map
Learn more about Intelligence Reports Advanced by navigating through the different resources.

Intelligence Reports Learning Map

Learn more about Intelligence Reports by navigating through the different resources.

View & Share Dashboards Create Pivot Tables

Get Started with Intelligence Reports
Trailhead: Get Started with Dashboards Trailhead: Explore Your Data with Pivot
Trailhead: Get to Know Intelligence Reports
Pre-Configured Dashboards Tables
User Roles and Permissions in Intelligence
Sharing Dashboard Pages and Widgets Create a Pivot Table in Intelligence Reports
Reports
Customize a Pivot Table in Intelligence
Overview of Data in Intelligence Reports
Reports
Dimensions and Measurements
Export a Pivot Table in Intelligence Reports

Create
Reports Learn More

65
Marketing Cloud Einstein and Analytics Start Learning About Intelligence Reports

Trailhead: Create Scheduled Reports Trailhead: Intelligence Reports for

Create a Report Engagement

Set Report Schedule and Delivery Method Trailhead: Intelligence Reports for
Engagement Advanced
View Report History

Intelligence Reports Advanced Learning Map

Learn more about Intelligence Reports Advanced by navigating through the different resources.

Get Started with Intelligence Reports Create & Customize Collections and Query Your Data
Advanced Dashboards Trailhead: Get Familiar with Queries
Trailhead: Get to Know Intelligence Reports Trailhead: Customize Dashboard Pages Query Your Data with Query Builder
Advanced Video: Create a New Dashboard Query Your Data with SQL
User Roles and Permissions in Intelligence Video: Apply Filters to Dashboards and
Reports Create a Query with a Data Extension
Design Elements
Overview of Data in Intelligence Reports Query Export Options
Create a Collection
Dimensions and Measurements Customize Dashboard Pages

Install & Use Apps Use Calculated Fields Learn More

Trailhead: Install Cross-Channel Solutions Trailhead: Calculated Measurements and Trailhead: Intelligence Reports for
Available Cross-Channel Apps Dimensions Engagement Advanced
Create a Calculated Dimension Trailhead: Intelligence Reports for
Calculated Dimensions Use Cases Engagement Advanced: Queries

Create a Calculated Measurement

Calculated Measurements Use Cases

66
Marketing Cloud Einstein and Analytics User Roles and Permissions in Intelligence Reports

User Roles and Permissions in Intelligence Reports

To use Intelligence Reports for Engagement, your account must be assigned the Intelligence Reports
EDITIONS
for Engagement user role. The user role has the following permissions: Access, View and Export,
Schedule, and Create and Edit. Available in: Intelligence
Reports and Intelligence
Reports Advanced
User Role
Note: The Enable Intelligence Reports Integration checkbox doesn’t affect Intelligence
Reports. This checkbox is related to the Marketing Cloud connector.
Your account must be assigned the Intelligence Reports for Engagement user role. The following permissions are available:
• Access, View & Export
• Schedule
• Create & Edit

User Permissions
These tables explain each permission and the available actions you can perform per permission:

Action / Permission Access, View & Export Schedule Create & Edit
View & Export Dashboards

Create & Export Pivot Tables

Save, Edit & Delete Pivot Tables

Schedule Report

Here are additional actions available with Intelligence Reports for Engagement Advanced:

Action / Permission Access, View & Export Schedule Create & Edit
Create & Customize Dashboards

Create Calculated Dimensions

and Measurements

Install Apps

Consume Cross-Channel Apps

Query Data Lake

Connect and Query Data

Extensions

This table displays how each permission affects the different Marketing Cloud User Roles:

67
Marketing Cloud Einstein and Analytics Access Intelligence Reports

MC Role / Permission Access, View & Export Schedule Create & Edit
Admin or Marketing Cloud
Administrator

Analyst or Marketing Cloud

Channel Manager or Marketing
Cloud Content Editor

Marketing Cloud Viewer

SEE ALSO:
Assign a Role to a Marketing Cloud User

Access Intelligence Reports

To access Intelligence Reports for Engagement, you need the required user role assigned to your
EDITIONS
account. When assigning the user role, you can also assign permissions in Intelligence Reports. For
example, you can create pivot tables, but you can’t edit or save them. Available in: Intelligence
Note: If you purchased Intelligence Reports for Engagement Advanced, all the advanced Reports and Intelligence
Reports Advanced
features are automatically enabled in your account. No other steps are required.
You can only log into one instance of Marketing Cloud Intelligence at a time – you can’t log into
Marketing Cloud Intelligence and Intelligence Reports for Engagement at the same time. If you must be logged into both, you can log
into one instance using Chrome Incognito mode.
The first time you activate Intelligence Reports for Engagement, up to 90 days of historical data is available. From that point on, the data
is retained for 2 years.

Note: If you don’t see the Intelligence Reports tab, it’s possible that you don’t have the required permissions, or that Intelligence
Reports hasn’t been enabled in your account.
To access Intelligence Reports for Engagement, click Analytics Builder > Intelligence Reports.

You can access Intelligence Reports in the context of the enterprise unit, or via the child business unit, which affects the data you see.
Enterprise versus Business Unit
• Enterprise: If you access Intelligence Reports for Engagement via an enterprise account, you can access all the data for all the
business units that are in the enterprise account.
• Business Unit: If you access Intelligence Reports for Engagement via a specific business unit, you can see only the data pertaining
to that business unit. You can only filter by entities in that unit.

68
Marketing Cloud Einstein and Analytics Overview of Data in Intelligence Reports

Overview of Data in Intelligence Reports

Intelligence Reports for Engagement displays both Email, Push, and Journey campaign-level data.
EDITIONS
Intelligence Reports for Engagement doesn’t display subscriber-level data or event-level data.
However, subscriber-level data can be used to generate campaign-level analytics. With Intelligence Available in: Intelligence
Reports for Engagement you can see how many emails or messages were opened, delivered, and Reports and Intelligence
clicked. The data that is displayed is daily aggregated metrics. For example, you can see the number Reports Advanced
of send and open rates per day, during the last 90 days, for a specific campaign.
Important Information about Data in Intelligence Reports
• Data retention — The first time you activate Intelligence Reports for Marketing Cloud, up to 90 days of historical data is available.
From that point on, historical data is retained for 2 years. The 2 years is according to the event date, meaning any event that happens
after 2 years doesn’t appear.

Note: Historical data that’s over 90 days can’t be processed; therefore if you’re encountering issues with data that’s older than
90 days we recommend you open a ticket as soon as you encounter missing data.

• Data refresh — Data is refreshed every 24 hours. Each account has its own time for daily refresh, and it can’t be set.
• Data retrieval — If a failure in data retrieval from Marketing Cloud to Intelligence Reports occurs, the process retries every few
hours. Any other data is reprocessed the following day. Such failures are monitored internally. The user isn’t notified of an error.
However, even with an error, you can keep using Intelligence Reports and retrieve reports based on existing data.
• Data deletion — When you delete a contact record for one or more subscribers within Marketing Cloud, personal information for
those contacts is removed from Intelligence Reports within 90 days. Also, when your Intelligence Reports subscription is terminated,
your customer data is deleted in accordance with the Marketing Trust and Compliance Documentation.
• Data migration— Data migration between stacks isn’t supported in Intelligence Reports. If you must migrate, support can help
with the migration; however historical data won’t be brought over. Contact your Marketing Cloud representative for more information.
• Time zone — Daily data is presented (aggregated) according to the time zone set in your enterprise’s business unit settings. All
business units that belong to the enterprise reflect the enterprise’s time zone.
– If you change the time zone, it doesn’t affect past data, only data collected after the change.
– If you log into Intelligence Reports for Engagement after the change, the time zone is updated automatically. However, if you
don’t log in right after the change, then it can take up to 7 days for the change to take place.

Available Data Elements

There are two types of data elements available: dimensions and measurements.
• Dimensions — Qualitative non-numerical data that you can't count, for example campaign name and campaign ID.
• Measurements — Quantitative numerical data that you can count, for example, number of clicks and emails opened.
If you’re using Advanced Intelligence Reports, you can also create calculated data element fields:
• Calculated Dimensions — Non-numerical fields or dimensions that you can create on top of your existing data. These queries can
be referenced to from reports and pivot tables, and they can support a variety of functions and logical conditions.
• Calculated Measurements — Numerical custom calculations that you can create on top of your existing data. You can reference
dimensions and measurements along with a number of different functions and operators.
For a full list of all the measurements and dimensions that are available, see Dimensions and Measurements.
Measurements are associated with dimensions of the same time. For example, opens are associated with the business unit name according
to that same day. If you change the name of the business unit, the new data is associated with the new business unit name. And, you
could see split data with the old name as well. When you assign an email to a campaign, this campaign assignment only picks up for
new sends. It doesn’t pick up retroactive sends.

69
Marketing Cloud Einstein and Analytics Dimensions and Measurements

Dimensions and Measurements

Dimensions and measurements are included when viewing dashboards, pivot tables, and reports.
EDITIONS
Use categories to find the data that’s most relevant to you.
Available in: Intelligence
Reports and Intelligence
Omni-Channel Dimensions and Measurements
Reports Advanced
The fields listed in this table refer only to the fields you see in Dashboards, Pivot Tables, and Reports.
These fields are different from the ones you see when you use Queries in Intelligence Reports
Advanced. For more information about the different fields in Queries, see Queries Data View.

Category Field Name Type Description

Time Attributes Event Date (Day, Week, Month) Dimension The date an event such as an open or
click occurred.

Send Date (Day, Week, Month) Dimension The date that the originating message
was sent.

Enterprise or Business Unit Business Unit Dimension The name of the business unit that
sent the message.

Business Unit ID Dimension The ID of the business unit.

Enterprise ID Dimension The ID of the enterprise account.

Audience Attributes Audience Name Dimension The name of the audience that the
(Not available for triggered email or message was sent to.
mobile push messages, or Audience name refers to the
in-app messages.) Publication List for Journey sends.
Note: Only 1 audience is supported.

Audience Type Dimension The audience type: List or Data

Extension.

Journey Attributes Journey ID Dimension The internal unique identifier of the

(Only available if you have journey and its version.
Journey Builder enabled in your Journey Name Dimension The journey name.
account.)
For Push data, not all messages are
assigned a journey name.

Journey Version Dimension The journey version.

Journey Status Dimension The journey status: Draft, Running,

Paused, Finishing, or Stopped.

Journey Activity Name Dimension The journey activity name.

Journey Activity Type Dimension The journey activity type.

Journey Description Dimension The journey description.

Journey Created Date Dimension The date the journey was created.

70
Marketing Cloud Einstein and Analytics Dimensions and Measurements

Category Field Name Type Description

Journey Last Published Date Dimension The last date that the journey was
published.

Journey Modified Date Dimension The last date that the journey was
modified.

Contact Entry Mode Dimension This mode dictates when the contact
is eligible to enter a journey.

Campaign Attributes Campaign Dimension The Marketing Cloud Campaign at the

time of the send (if assigned).
Note: Only 1 campaign is supported.

Campaign ID Dimension The campaign’s internal ID.

Campaign Code Dimension The campaign’s code, as given by the

user.

Campaign Start Date Dimension The campaign’s start date.

Campaign End Date Dimension The campaign’s end date.

Campaign Status Dimension The campaign’s status.

Email Dimensions and Measurements

Category Field Name Type Description
Email Attributes Email Job ID Dimension The unique identifier of the
email sent.

Email Content Name Dimension The email name at the time of

send.

Email Send Name Dimension The name of the send definition

used to send the email. (This
data is currently partially
available.)

Email Subject Dimension The email subject at the time of

send.

Email Status Dimension The email job status at the time

of send.

Email Send Type Dimension The type of message sent.

• Triggered – Anything that
uses event-driven sending
queues, such as SOAP
triggered sends and

71
Marketing Cloud Einstein and Analytics Dimensions and Measurements

Category Field Name Type Description

Transaction Journey and
REST APIs.
• Standard – Includes
batch-based sending, such
as sending by a list or by a
data extension through
Automation Studio or Email
Studio.

Email Send Classification Type Dimension This field represents the value
selected in the CAN-SPAM
Classification and can display
either Commercial or
Transactional values.
For more information about
send classifications, see Send
Classifications in Marketing
Cloud.

Email Test Indicator Dimension A flag that indicates the

message was part of a test send.

Email Sender Address Dimension The email sender’s address.

Email Sender Name Dimension The email sender’s name.

Email Sender IP Dimension The IP address of the sent

message. The IP address can be
empty in cases where the email
wasn’t sent successfully.
Note: From June 2022 and
onwards, triggered emails are
supported.

Email Pre-Header Dimension The email preheader. A

preheader is the text following
the subject line when an email
is previewed. A preheader is one
of the first three items that a
subscriber sees when viewing
an email.

Email Domain Dimension The email domain for the

message that was sent, such as
yahoo.com or gmail.com.

72
Marketing Cloud Einstein and Analytics Dimensions and Measurements

Category Field Name Type Description

Email Country Code Dimension The country code of the user
who engaged with the email.
• Only available for the U.S.
• Not always available or
accurate due to
dependencies on mail proxy
servers, VPNs, and privacy
controls.

Region Code Dimension The state of the user who

engaged with the email.
• Only available for the U.S.
• Not always available or
accurate.

User Agent Email Browser Model Dimension The browser model for the email
Disclaimer: Salesforce doesn’t that was sent, such as Firefox or
guarantee the accuracy or Chrome. (Only available for
completeness of this data. Use opens and clicks.)
as reference only. Email Browser Name Dimension The browser name for the email
that was sent, such as Chrome
96 or Edge 96. (Only available for
opens and clicks.)

Email Device Model Dimension The device model for the email
that was sent. (Only available for
opens and clicks.)

Email Device Name Dimension The device name for the email
was sent. (Only available for
opens and clicks.)

Email Client Model Dimension The email client model for the
email that was sent. For
example, Outlook. (Only
available for opens and clicks.)

Email Client Name Dimension The email client name for the
email that was sent. For
example, Outlook 2013. (Only
available for opens and clicks.)

Email Device OS Model Dimension The operating system model

used for the email that was sent.
(Only available for opens and
clicks.)

73
Marketing Cloud Einstein and Analytics Dimensions and Measurements

Category Field Name Type Description

Email Device OS Name Dimension The operating system device
name used for the email that
was sent. (Only available for
opens and clicks.)

Email Device Type Dimension Type of device used, mobile, or

desktop. (Only available for
opens and clicks.)

Email Feature Phone Dimension Indicates if a feature phone

received the message. Feature
phones are older-generation
mobile phones and are mostly
used in Japan. (Only available for
opens and clicks.)

Email Link Alias Dimension The actual link that was clicked
within the email. Only works for
links that are assigned a link
alias. (Only available for clicks.)

Email Delivery Email Sends Measurement The number of emails sent.

Includes successful and
unsuccessful sends.

Email Bounces Measurement The number of blocks and hard

and soft bounces received from
the sender’s email address.

Email Bounces Hard Measurement The number of hard bounces.

Email Bounces Soft Measurement The number of soft bounces.

Email Bounces Block Measurement The number of blocked bounces.

Email Bounces Technical Measurement The number of technical

bounces.

Email Bounces Unknown Measurement The number of unknown

bounces.

Email Bounces Unclassified Measurement The number of unclassified

bounces. This is used when the
bounce type is empty.

Email Bounce Type Dimension The email bounce type:

• Block – Number of bounces
resulting from a complaint,
blocklist, content, URL block,
or authentication error.
• Hard – Number of bounces
caused by an unknown

74
Marketing Cloud Einstein and Analytics Dimensions and Measurements

Category Field Name Type Description

domain or user, or syntax
error.
• Soft – Number of bounces
resulting from a full or
temporarily inactive
mailbox, or temporary
domain failure.
• Technical – Number of
bounces caused by the
server, data format, or
network error.
• Unknown – Number of
bounces that occurred for
an unknown reason.
Note: Bounce rate can’t be
attributed to a specific bounce
type because sends aren’t
attributed to a specific bounce
type.

Email Deliveries Calculated Measurement The number of emails delivered.

Calculation: (Number of Sends)
- (Number of Bounces).

Email Delivery Rate Calculated Measurement Percentage of emails delivered.

Calculation: (Number of sends)
- (Number of Bounces) /
(Number of Sends).

Email Bounce Rate Calculated Measurement Percentage of emails that

bounced. Calculation: (Number
of Bounces) / (Number of
Sends).

Email Engagement Email Unique Opens Measurement The number of opens by distinct
subscribers. Any other attributes
about unique opens show
information relevant to the first
open for that user.
Note: Sometimes this
measurement doesn’t accurately
reflect actual engagement. Tell
me more.

Email Total Opens Measurement The total number of emails

opened.

75
Marketing Cloud Einstein and Analytics Dimensions and Measurements

Category Field Name Type Description

Emails Unique Clicks Measurement The number of clicks by distinct
subscribers. Any other attributes
about unique clicks show
information relevant to the first
click for that user.
Note: This measurement also
includes unsubscribe clicks.

Email Total Clicks Measurement The total number of email clicks.

Email Unique Unsubscribes Measurement The total number of unique

unsubscribes. Any other
attributes about unique
unsubscribes show information
relevant to the first click for that
user.

Email Total Unsubscribe Measurement The total number of users who

unsubscribed.

Email Open Rate Calculated Measurement Percentage of email opens.

Calculation: (Unique Opens) /
(Deliveries).
Note: Sometimes this
measurement doesn’t accurately
reflect actual engagement. Tell
me more.

Email Click Rate Calculated Measurement Percentage of email clicks.

Calculation: (Unique Clicks) /
(Delivered Emails)

Email Click-To-Open Rate Calculated Measurement Percentage of email clicks to

opens. Calculation: (Unique
Clicks) / (Unique Opens)
Note: This measurement may
not accurately reflect actual
engagement. Tell me more.

Email Unsubscribe Rate Calculated Measurement Percentage of email

unsubscribes. Calculation:
(Unique Subscribes) / (Delivered
Emails)

Email Total Complaints Measurement The total number of complaints

received by unique IPs. A
complaint is logged when a

76
Marketing Cloud Einstein and Analytics Dimensions and Measurements

Category Field Name Type Description

subscriber flags the email as
spam. Note: Most email
providers don’t include this data.

Email Unique Complaints Measurement The number of complaints by

distinct users. Note: Most email
providers don’t include this data.

Email Studio Total Conversions Measurement The number of conversions an

email has received by unique IPs.

Email Studio Unique Measurement The number of conversions by

Conversions distinct users.

Email Click Event Lag Days Calculated Measurement The average time in days that
passed between the click and
send time.

Push Dimensions and Measurements

Category Field Name Type Description
Push Notification Attributes Push Content Name Dimension The name of the content used
in the send.

Push Send Name Dimension The name of the send definition.

For Mobile Studio sends: the
Message Name, for Transactional
API sends: the DefinitionKey, for
Journey Builder sends: the
Activity Name.

Push Send Type Dimension The type of message sent:

• User-Initiated — The
message was sent via
Mobile Studio.
• API Triggered — The
message was triggered via
an API event.
• Automation Studio — The
message was sent via
Automation Studio.
• Journey — The message
was sent via Journey Builder.

Push Send ID Dimension The unique identifier for the

send definition, the Send Name.

77
Marketing Cloud Einstein and Analytics Dimensions and Measurements

Category Field Name Type Description

This is a separate identifier from
the job ID.

Push Title Dimension The title used in the message

content that’s shown to the end
user.

Push Notification Delivery Push Sends Measurement The number of push

notifications sent per device.

Push Bounces Measurement The total number of messages

rejected by Apple or Google.
Bounces often occur as a result
of invalid push tokens or invalid
sending credentials.

Push Deliveries Calculated Measurement The total number of messages

accepted by Apple or Google.

Push Bounce Rate Calculated Measurement Percentage of messages rejected

by Apple or Google. Calculation:
(Bounces) / (Sends).

Push Delivery Rate Calculated Measurement Percentage of messages

accepted by Apple or Google.
Calculation: (Deliveries) /
(Sends).

Push Not Sent Measurement The sum of failures for sends.

Push Notification Engagement Push Opens Measurement The total number of messages
opened.
• Push messages can only be
opened one time per device.
• The timestamp for open
events is according to the
end user’s device.
• In some cases it can take a
few days for an open event
to be reported to
Intelligence Reports.
Therefore, open events that
occurred 21 days before the
event reached Intelligence
Reports are omitted.
• The Push Message Summary
Report can show more
opens than Intelligence
Reports because it doesn’t

78
Marketing Cloud Einstein and Analytics Dimensions and Measurements

Category Field Name Type Description

take duplicate opens into
account.

Push Open Rate Calculated Measurement Percentage of messages opened.

Calculation: (Opens) /
(Deliveries). Available for
calculations at the device level.

In-App Dimensions and Measurements

In-app data is collected from the moment of provisioning, so historical data isn’t tracked. In some cases, events such as clicks or dismisses
of sends that occurred before provisioning can appear in the data. In these situations, no send date is assigned to these events, and
they’re filtered out of the dashboards.

Category Field Name Type Description

In-App Attributes In-App Content Name Dimension The name of the content (from
Content Builder) that was used
within the send. For Journey
Builder Sends, the Content Asset
Name=In-App Content Name.

In-App Send Name Dimension The name of the message for the
marketer to reference. For
Journey Builder Sends, the
Journey Builder Activity
Name=In-App Send Name.

In-App Send Type Dimension The type of message sent:

• User-Initiated — The
message was sent via
Mobile Studio.
• API Triggered — The
message was triggered via
an API event.
• Automation Studio — The
message was sent via
Automation Studio.
• Journey — The message
was sent via Journey Builder.

In-App Send ID Dimension The unique identifier for the

Send Name. This isn’t the job ID.
For Journey Builder Sends, the
MessageID=In-App Send ID.

79
Marketing Cloud Einstein and Analytics Dimensions and Measurements

Category Field Name Type Description

In-App Title Dimension The title used in the message
content that’s shown to the end
user.

In-App Message Layout Dimension The layout of the in-app

message: Banner, Full Page, and
Modal.

In-App Button ID Dimension The ID of the button.

Note: This is only relevant for
clicks.

In-App Button Label Dimension The label of the clicked button.

In-App Dismiss Type Dimension If a dismiss event occurred, this

metric indicates the type.
Possible values are AutoDismiss,
ButtonClicked, or Closed.

In-App Delivery Attributes In-App Unique Sends Measurement The unique sum of sends
successfully rendered (Successful
Published); calculated at the
Contact level.

In-App Device Deliveries Measurement The number of downloads by

devices. This number is typically
higher than the number of
Unique Sends. Sends are
calculated by contact, while this
metric is calculated by device.
The difference arises when
contacts have more than one
device.

In-App Device Displays Measurement The total in-app displays per

device.

In-App Device Display Rate Measurement The device display rate.

Calculation: (Device Displays /
Device Deliveries)

In-App Device Button Clicks Measurement Total button clicks across

devices.

In-App Device Button Click Rate Measurement The device button click rate.
Calculation: (Device Button
Clicks / Device Displays)

In-App Device Dismisses Measurement The total number of times the

dismiss button was clicked
across devices.

80
Marketing Cloud Einstein and Analytics Send Date Versus Event Date

Category Field Name Type Description

In-App Device Dismiss Rate Measurement The device dismiss rate.
Calculation: (Device Dismisses /
Device Displays)

In-App Avg. Display Time Measurement The average amount of time the
in-app message was displayed.
Calculation: (Total time in app /
device displays)

Send Date Versus Event Date

All engagement events in Intelligence Reports have two date dimensions: Event, and send.
EDITIONS
• Event date - The date the event occurred (for example, email opened).
• Send date - The date the message for this event was sent. Available in: Intelligence
Reports and Intelligence
The two date dimensions are especially important when looking at opens and clicks. For example, Reports Advanced
when reporting on clicks or opens, setting the Event Date filter to the last 30 days without setting
a Send Date filter returns data for all emails that were clicked during the last 30 days, regardless of
when they were sent. The results could include emails that were sent 31 or more days earlier.
Both date dimensions are used in Intelligence Reports but appear differently in pivot tables, reports, and dashboards.
Pivot Tables — All pivot tables have an Event Date filter. When selecting the date range, all events from the specified time are included,
regardless of the send date.

To see the number of events that occurred since the send date, add the Send Date dimension to your pivot table.

81
Marketing Cloud Einstein and Analytics Send Date Versus Event Date

You can also filter your pivot table to include only send dates. Create a filter using the Send Date dimension. For more information, see
Applying Filters to Pivot Tables and Reports on page 126.

Reports — All reports have an Event Date filter. When selecting the date range, all events from the specified time are included.

82
Marketing Cloud Einstein and Analytics Send Date Versus Event Date

To filter your report to include only certain send dates, create a filter using the Send Date dimension. For more information, see Applying
Filters to Pivot Tables and Reports on page 126.
Dashboards — For out-of-the-box dashboards, you can control only the send date. The event date filter is preset to include all dates.
If you’re a Intelligence Reports Advanced user, you can control the event date at the top of the page and build the dashboard according
to your needs. For more information, see Customize Dashboard Pages on page 97.

83
Marketing Cloud Einstein and Analytics Dashboards

Dashboards
Dashboards provide an out-of-the box view of your Email, Push, and Journey data. With dashboards,
EDITIONS
you gain valuable insights and can quickly identify trends or anomalies. With the premium Advanced
version, you can also create and edit dashboards. Available in: Intelligence
All dashboards contain dimensions and measurements to analyze your data. For more information, Reports and Intelligence
see Dimensions and Measurements Reports Advanced

Note: If you’re having trouble loading dashboards, make sure you allowlist the Intelligence
Reports domain/IP addresses for Intelligence Reports. For more information, see IP Addresses
for Inclusion on Allowlists in Marketing Cloud.
For more information about dashboards, click these links:

Pre-Configured Dashboards
Intelligence Reports for Engagement’s pre-configured dashboards provide valuable insights and help you quickly identify trends or
anomalies.
Create and Configure Dashboards
In Intelligence Reports Advanced you can create and customize dashboards to meet your business needs.
Apply Filters to Dashboards
Filters enable you to focus on the data most relevant to you. When you select a filter in a dashboard, it applies to all dashboards.

84
Marketing Cloud Einstein and Analytics Dashboards

Sharing Dashboard Pages and Widgets

Slack provides seamless collaboration with colleagues and clients. Marketing teams can work together and communicate on
campaigns and improve cross-functional work. You can share dashboards and widgets via Slack, email, or as downloaded local files.
You can also schedule when to share reports.

Pre-Configured Dashboards
Intelligence Reports for Engagement’s pre-configured dashboards provide valuable insights and
EDITIONS
help you quickly identify trends or anomalies.

Note: Available in: Intelligence

Reports and Intelligence
• All dashboards and their components refer to the send date, not the event date. If you Reports Advanced
want a report to refer to the event date, create a pivot table.
• All dashboards exclude test emails.
• Emails configured to Suppress from Send Reports aren't included in Intelligence Reports.

These dashboards are available to you:

Email Overview Dashboard

Get a high-level overview of your email campaigns, such as the number of emails sent, the open rate, delivery and engagement,
and the top- and bottom-performing journey emails.
Email Deliveries Dashboard
View your email delivery data, including key performance indicators (KPIs) such as sends, deliveries and bounces, and delivery
timelines.
Email Engagement Dashboard
A detailed look into your email engagement key performance indicators (KPIs), including opens, clicks, unsubscribes, and engagement
timelines.
Email Performance Dashboard
Get details of your email send data, including the open rate, click rate, unsubscribe rate, and performance funnel.
Journey Performance by Email Dashboard
Get an in-depth view into your email journey and activities performance data. It also provides a breakdown by domain, day of the
week, and audience.
Push Deliveries Dashboard
View your push notification delivery data and timelines. Get breakdowns by day of the week, mobile OS, and mobile app.
Push Engagement Dashboard
Get details about your push notification engagement key performance indicators (KPIs), including deliveries, opens, and open rate.
View breakdowns by day of the week, mobile OS, and mobile apps. You can export the dashboard and its widgets into different
formats.
Push Performance Dashboard
Get details about your push performance, including an overview of push sends, by looking at deliveries, delivery rate, and bounces.
View breakdowns by day of week, mobile OS, and mobile app.
Journey Performance by Push Dashboard
View your journey and push notification performance data. View breakdowns by day of the week, mobile OS, and mobile app.

85
Marketing Cloud Einstein and Analytics Dashboards

In-App Deliveries Dashboard

View your in-app delivery data including unique sends, message deliveries, device displays, and display rate. Get breakdowns by
day of the week, mobile operating system, and mobile app.
In-App Engagement Dashboard
Get details about your in-app engagement key performance indicators (KPIs), including device button clicks, device dismisses, device
button click rate and more. View breakdowns by day of the week, mobile OS, and mobile apps. You can export the dashboard and
its widgets into different formats.
In-App Performance Dashboard
Get details about your in-app message performance, including an overview of sends, by looking at deliveries, display rate, and
dismisses. View breakdowns by day of week, mobile OS, and mobile app.
Journey Performance by In-App Dashboard
View your journey and in-app message performance data. View breakdowns by day of the week, mobile operating system, and
mobile app.

Email Overview Dashboard

Get a high-level overview of your email campaigns, such as the number of emails sent, the open
EDITIONS
rate, delivery and engagement, and the top- and bottom-performing journey emails.
You can filter the email overview dashboard by: Available in: Intelligence
Reports and Intelligence
• Send date
Reports Advanced
• Business unit
• Campaign
After you select the filters, click Apply.

Note: Each section in this dashboard has a View More button that takes you to the corresponding dashboard for more details.

The email overview dashboard contains these sections:

• Delivery — Get a snapshot of how your email campaigns are performing in terms of sends and bounce rate.
– Sends — A graph that shows the number of emails sent within the filtered time period.
– Bounce Rate — A graph that shows the percentage of emails that didn’t reach the intended recipient.
– Timeline Graph — A graph that shows sends and bounce rates over time.

• Engagement — An overview of how your email campaigns are performing in terms of email opens.

Note: Open related measurements may not accurately reflect engagement. Tell me more.

– Open Rate — The percentage of emails opened within the filtered time period.
– Click to Open Rate — The rate of unique clicks to unique opens. This rate indicates how effective the email message, design,
and content performed, and whether it encouraged the recipient to act.
– Delivery & Engagement Timeline — A graph that shows the open rate and the click-to-open rate.

• Email Performance — Your email performance data.

– Conversion Funnel — Provides insight into the success of your email campaigns.
– Engagement Distribution — Your top 10 emails shown in a bubble chart. The x axis represents the open rate and the y axis
represents the click to open rate. An optimum email has the following traits:
• A high number of sends — The larger the bubble, the higher number of sends.

86
Marketing Cloud Einstein and Analytics Dashboards

• A high open rate and a high click-to-open rate appear at the top right corner of the graph.
The least desirable result is a large bubble in the bottom left corner of the graph because it indicates a high send rate with a low
open and click-to-open rate.

• Journey Performance by Email–Journey performance data.

Note: Only available if you have Journey Builder enabled in your account.

– Top five journeys–The top five email journeys by open rate.

– Bottom five journeys–The bottom five email journeys by open rate.

Email Deliveries Dashboard

View your email delivery data, including key performance indicators (KPIs) such as sends, deliveries
EDITIONS
and bounces, and delivery timelines.
You can filter the email deliveries dashboard by: Available in: Intelligence
Reports and Intelligence
• Send date
Reports Advanced
• Business unit
• Campaign
After you select the filters, click Apply.
The email deliveries dashboard contains these sections:
• Delivery KPIs – The top three KPIs for email deliveries within the filtered time period.

Note: Each section shows how the measurement performed in the previous period and whether it increased or decreased
compared to the current period. You can define the compare to period in the send date filter.
These KPIs include:
– Sends – The number of emails sent.
– Deliveries – The number of emails delivered.
– Bounce Rate – The percentage of the number of emails that didn’t reach the intended recipient.

• Delivery Timeline – The selected measurements over a timeline. You can also select the granularity that you want to filter the
graph by, for example, daily.
• Breakdowns – An analysis of the selected measurement.
– By Email Domain – A bar graph that shows the selected measurement divided by email domain.
– By Day of the Week – A table that shows how the selected measurement performed each day of the week. This table can help
you determine the best day to optimize your email campaigns.
– By Audience – A table that shows how each measurement performed per audience.

• Details – A table of your top 100 emails sent within the defined time frame, according to the selected measurement.

Note: You can sort each column in the table by ascending or descending order.

87
Marketing Cloud Einstein and Analytics Dashboards

Email Engagement Dashboard

A detailed look into your email engagement key performance indicators (KPIs), including opens,
EDITIONS
clicks, unsubscribes, and engagement timelines.
You can export the dashboard and its widgets into different formats. Available in: Intelligence
Reports and Intelligence
You can filter the email overview dashboard by:
Reports Advanced
• Send date
• Business unit
• Campaign
After you select the filters, click Apply.
The email engagement dashboard contains these sections:
• Engagement KPIs – The top KPIs for email engagement within the filtered time period. These KPIs include opens, clicks, unsubscribes,
the open rate, the click-to-open rate, and the unsubscribe rate.

Note:
– Opens, clicks, and unsubscribe metrics refer to uniques, not totals.
– Open related measurements may not accurately reflect engagement. Tell me more.
– Each section shows how the measurement performed in the previous period and whether it increased or decreased
compared to the current period.

• Engagement Timeline – Emails with the best engagement for the defined time period. Select the measurement you want to
display in the graph. You can also select the granularity you want to filter the graph by, such as monthly.
• Breakdowns – An analysis of the selected measurement.
– By Email Domain – A bar graph that shows the selected measurement divided by email domain.
– By Day of the Week – A table that shows how the selected measurement performed each day of the week. This table can help
you determine the best day to optimize your email campaigns.
– By Audience – A table that shows how each measurement performed per audience.

• Details – A table of your top 100 emails sent within the defined time frame, according to the selected measurement.

Note: Each column in the table can be sorted by ascending or descending order.

Email Performance Dashboard

Get details of your email send data, including the open rate, click rate, unsubscribe rate, and
EDITIONS
performance funnel.
You can filter the email performance dashboard by: Available in: Intelligence
Reports and Intelligence
• Send date
Reports Advanced
• Business unit
• Campaign
• Email name
• Email subject
After you select the filters, click Apply.
The email performance dashboard contains these sections:

88
Marketing Cloud Einstein and Analytics Dashboards

• Email Sends – A table that shows how your emails performed according to the measurements you selected.

Note: Open related measurements may not accurately reflect engagement. Tell me more.

• Breakdowns – An analysis of the selected measurement.

– By Email Domain – A bar graph that shows the selected measurement divided by email domain.
– By Day of the Week – A table that shows how the selected measurement performed each day of the week. This table can help
you determine the best day to optimize your email campaigns.
– By Audience – A table that shows how each measurement performed per audience.

Journey Performance by Email Dashboard

Get an in-depth view into your email journey and activities performance data. It also provides a
EDITIONS
breakdown by domain, day of the week, and audience.

Note: Only available if you have Journey Builder enabled in your account. Available in: Intelligence
Reports and Intelligence
You can filter the journey performance by email dashboard by: Reports Advanced
• Send date
• Business unit
• Campaign
• Journey name
• Journey version
• Journey activity name
After you select the filters, click Apply.
The journey performance by email dashboard contains these sections:
• Journeys & Activities – A pivot table that shows how your journeys performed according to the measurements you selected. It
can help you quickly compare your journey performances to identify which journeys are performing the best or worst.

Note: Open related measurements may not accurately reflect engagement. Tell me more.

• Breakdowns – An analysis of the selected measurement.

– By Email Domain – A bar graph that shows the selected measurement divided by email domain.
– By Day of the Week – A table that shows how the selected measurement performed each day of the week. This table can help
you determine the best day to optimize your email campaigns.
– By Audience – A table that shows how each measurement performed per audience.

Push Deliveries Dashboard

View your push notification delivery data and timelines. Get breakdowns by day of the week, mobile
EDITIONS
OS, and mobile app.

Note: This dashboard includes push notification sends. It doesn’t include inbox or in-app Available in: Intelligence
sends. Reports and Intelligence
Reports Advanced
You can filter the push deliveries dashboard by:
• Send date

89
Marketing Cloud Einstein and Analytics Dashboards

• Business unit
• Campaign
• Mobile OS
• Mobile app
After you select the filters, click Apply.
The push deliveries dashboard contains these sections:
• Delivery KPIs — Top three KPIs for email deliveries within the filtered time period. These KPIs include:
– Sends — Total number of messages sent from Marketing Cloud to Apple or Google.
– Deliveries — Total number of messages accepted by Apple or Google.
– Bounce Rate — Percentage of messages rejected by Apple or Google. Calculation: (Bounces) / (Sends).

Note: Each section shows how the measurement performed in the previous period and whether it increased or decreased.
You can define the compare to period with the send date filter.

• Delivery Timeline — Displays the selected measurements over a timeline. You can also select the granularity that you want to
filter the graph by, for example, sends.
• Breakdowns — This section shows an analysis of the selected measurement.
– By Day of the Week — A table that shows how the selected measurement performed each day of the week. This table can
help you determine the best day to optimize your push notifications.
– By Mobile OS— A bar graph that shows the selected measurement divided by the mobile operating system.
– By Mobile App – A table that shows how each measurement performed per mobile app.

• Audience Details — A table that displays your audience details according to type, sends, deliveries and bounce rate. Audience
Name refers to the name of the audience. Audience Type refers to a list or data extension.
• Send Details — A table of your top-100 push notifications sent within the defined time frame, according to the selected measurement.

Push Engagement Dashboard

Get details about your push notification engagement key performance indicators (KPIs), including
EDITIONS
deliveries, opens, and open rate. View breakdowns by day of the week, mobile OS, and mobile apps.
You can export the dashboard and its widgets into different formats. Available in: Intelligence
Note: This dashboard includes push notification sends. It doesn’t include inbox or in-app Reports and Intelligence
Reports Advanced
sends.
You can filter the push engagement dashboard by:
• Send date
• Business unit
• Campaign
• Mobile OS
• Mobile app
After you select filters, click Apply.
The push engagement dashboard contains these sections:
• Engagement KPIs — The top KPIs for push engagement within the filtered time period. These KPIs include opens, and open rate.
– Opens - The total number of messages opened.

90
Marketing Cloud Einstein and Analytics Dashboards

– Open Rate - The percentage of messages opened. Calculation: (Opens) / (Deliveries)

Note: Each section shows how the measurement performed in the previous period and whether it increased or decreased
compared to the current period.

• Engagement Timeline — A graph that shows pushes with the best engagement for the defined time period.
• Breakdowns — An analysis of the selected measurement.
– By Day of the Week — A table that shows how the selected measurement performed for each day of the week. This table can
help you determine the best day to optimize your push notifications.
– By Mobile OS – A bar graph that shows the selected measurement divided by the mobile operating system.
– By Mobile App — A table that shows how each measurement performed per mobile app.

• Audience Details — A detailed list of your audience’s engagement according to type, deliveries, opens and open rate. Audience
Name refers to the name of the audience. Audience Type refers to a list or data extension.
• Send Details — A table of your top 100 pushes sent within the defined time frame, according to the selected measurement.

Note: Each column in the table can be sorted by ascending or descending order.

Push Performance Dashboard

Get details about your push performance, including an overview of push sends, by looking at
EDITIONS
deliveries, delivery rate, and bounces. View breakdowns by day of week, mobile OS, and mobile
app. Available in: Intelligence
Note: This dashboard includes push notification sends. It doesn’t include inbox or in-app Reports and Intelligence
Reports Advanced
sends.
You can filter the push performance dashboard by:
• Send date
• Business unit
• Campaign
• Mobile app
• Mobile device OS
• Push send name
• Push title
After you select filters, click Apply.
The push performance dashboard contains these sections:
• Push Sends — A graph that shows a view of push performance. Turn on or off these dimensions and measurements: sends, deliveries,
delivery rate, bounces, bounce rate, opens, and open rate.
• Breakdowns — An analysis of the selected measurement.
– By Day of the Week — A table that shows how the selected measurement performed for each day of the week. This table can
help you determine the best day to optimize your push notifications.
– By Mobile OS – A bar graph that shows the selected measurement divided by the mobile operating system.
– By Mobile App — A table that shows how each measurement performed per mobile app.

• Audience Details — A detailed list of your audience’s engagement according to type, sends, bounce rate and open rate. Audience
Name refers to the name of the audience. Audience Type refers to a list or data extension.

91
Marketing Cloud Einstein and Analytics Dashboards

Journey Performance by Push Dashboard

View your journey and push notification performance data. View breakdowns by day of the week,
EDITIONS
mobile OS, and mobile app.

Note: Only available if you have Journey Builder enabled in your account. Available in: Intelligence
Reports and Intelligence
Note: This dashboard includes push notification sends. It doesn’t include inbox or in-app Reports Advanced
sends.
You can filter the journey performance by push dashboard by:
• Send date
• Business unit
• Campaign
• Mobile OS
• Mobile app
• Journey name
• Journey version
• Journey activity name
After you select filters, click Apply.
The journey performance by push dashboard contains these sections:
• Journeys & Activities — A pivot table that shows how your journeys performed according to measurements. Use the pivot table
to compare your journey performances.
• Breakdowns — An in-depth analysis of the measurement that you selected.
– By Day of the Week — A table that shows how the selected measurement performed on each day of the week. This table can
help you determine the best day to optimize your push notifications.
– By Mobile OS — A bar graph that shows the selected measurement divided by mobile operating system.
– By Mobile App — A table that shows how each measurement performed per mobile app.

• Audience Details — A detailed list of your audience’s engagement according to type, deliveries, opens, and open rate. Audience
Name refers to the name of the audience. Audience Type refers to a list or data extension.

Note: Audience data isn’t available for triggered mobile push messages.

In-App Deliveries Dashboard

View your in-app delivery data including unique sends, message deliveries, device displays, and
EDITIONS
display rate. Get breakdowns by day of the week, mobile operating system, and mobile app.
You can filter the in-app deliveries dashboard by: Available in: Intelligence
Reports and Intelligence
• Send date
Reports Advanced
• Business unit
• Campaign
• Mobile OS
• Mobile app
After you select the filters, click Apply.

92
Marketing Cloud Einstein and Analytics Dashboards

The in-app deliveries dashboard contains these sections:

• Delivery KPIs—Top KPIs for message deliveries within the filtered time period. These KPIs include:
– Unique Sends —The unique sum of sends that were successfully rendered.
– Device Deliveries—The number of downloads by devices.
– Device Displays —The total in-app displays per device.
– Device Display Rate—The device display rate. Calculation: (Device Displays / Device Deliveries).

Note: Each section shows how the measurement performed in the previous period and whether it increased or decreased.
You can define the compare to period with the send date filter.

• Delivery Timeline—Displays the selected measurements over a timeline. You can also select the granularity that you want to filter
the graph by, for example, unique sends.
• Breakdowns—This section shows an analysis of the selected measurement.
– By Day of the Week—A table that shows how the selected measurement performed each day of the week. This table can help
you determine the best day to optimize your push notifications.
– By Mobile OS—A bar graph that shows the selected measurement divided by the mobile operating system.
– By Mobile App—A table that shows how each measurement performed per mobile app.

• Send Details—A table of your top-100 in-app messages within the defined time frame, according to the selected measurement.

In-App Engagement Dashboard

Get details about your in-app engagement key performance indicators (KPIs), including device
EDITIONS
button clicks, device dismisses, device button click rate and more. View breakdowns by day of the
week, mobile OS, and mobile apps. You can export the dashboard and its widgets into different Available in: Intelligence
formats. Reports and Intelligence
You can filter the in-app engagement dashboard by: Reports Advanced

• Send date
• Business unit
• Campaign
• Mobile OS
• Mobile app
After you select the filters, click Apply.
In-app engagement dashboard contains these sections:
• Engagement KPIs —The top KPIs for in-app engagement within the filtered time period.
– Device Button Clicks—The number of times the message was clicked across devices.
– Device Dismisses—The total number of times the dismiss button was clicked across devices.
– Device Button Click Rate—The device button click rate. Calculation: (Device Button Clicks / Device Displays)
– Device Dismiss Rate—The number of device dismisses. Calculation: (Device Dismisses / Device Displays)
– Avg. Display Time—The average amount of time the in-app message was displayed.

Note: Each section shows how the measurement performed in the previous period and whether it increased or decreased.
You can define the compare to period with the send date filter.

93
Marketing Cloud Einstein and Analytics Dashboards

• Engagement Timeline —A graph that shows in-app messages with the best engagement for the defined time period.
• Breakdowns—This section shows an analysis of the selected measurement.
– By Day of the Week—A table that shows how the selected measurement performed each day of the week. This table can help
you determine the best day to optimize your push notifications.
– By Mobile OS—A bar graph that shows the selected measurement divided by the mobile operating system.
– By Mobile App—A table that shows how each measurement performed per mobile app.

• Send Details—A table of your top-100 in-app messages within the defined time frame, according to the selected measurement.

In-App Performance Dashboard

Get details about your in-app message performance, including an overview of sends, by looking
EDITIONS
at deliveries, display rate, and dismisses. View breakdowns by day of week, mobile OS, and mobile
app. Available in: Intelligence
You can filter the in-app performance dashboard by: Reports and Intelligence
Reports Advanced
• Send date
• Business unit
• Campaign
• Mobile app
• Mobile OS
• In app send name
• In app send title
After you select the filters, click Apply.
The In-app performance dashboard contains these sections:
• In-App Message Sends — A graph that shows a view of in-app performance. Turn on or off these dimensions and measurements:
unique sends, device deliveries, device displays, device display rates, device button clicks, device button click rates, device dismisses,
device dismiss rates and average display times.
• Breakdowns—This section shows an analysis of the selected measurement.
– By Day of the Week—A table that shows how the selected measurement performed each day of the week. This table can help
you determine the best day to optimize your push notifications.
– By Mobile OS—A bar graph that shows the selected measurement divided by the mobile operating system.
– By Mobile App—A table that shows how each measurement performed per mobile app.

Journey Performance by In-App Dashboard

View your journey and in-app message performance data. View breakdowns by day of the week,
EDITIONS
mobile operating system, and mobile app.

Note: Only available if you have Journey Builder enabled in your account. Available in: Intelligence
Reports and Intelligence
You can filter the journey performance by in-app dashboard by: Reports Advanced
• Send date
• Business unit
• Campaign

94
Marketing Cloud Einstein and Analytics Dashboards

• Mobile OS
• Mobile app
• Journey name
• Journey version
• Journey activity name
After you select the filters, click Apply.
The journey performance by in-app dashboard contains these sections:
• Journeys & Activities — A pivot table that shows how your journeys performed according to measurements. Use the pivot table
to compare your journey performances.
• Breakdowns—This section shows an analysis of the selected measurement.
– By Day of the Week—A table that shows how the selected measurement performed each day of the week. This table can help
you determine the best day to optimize your push notifications.
– By Mobile OS—A bar graph that shows the selected measurement divided by the mobile operating system.
– By Mobile App—A table that shows how each measurement performed per mobile app.

Create and Configure Dashboards

In Intelligence Reports Advanced you can create and customize dashboards to meet your business
EDITIONS
needs.

Note: You can create up to 50 dashboards in Intelligence Reports Advanced. Available in: Intelligence
Reports Advanced
If it’s your first time creating dashboards, or you need a refresher, check out these short instructional
videos:
• Watch a video

• Watch a video

Collections
Collections are like notebooks, and the pages inside the notebooks are what we call dashboard pages. Collections allow you to
organize related dashboards together.
Dashboard Pages
Dashboard pages segment your collections so you can divide up your data according to your preferences. Each page can be
customized and filtered, so you can modify the design and remove any unwanted data.

Collections
Collections are like notebooks, and the pages inside the notebooks are what we call dashboard
EDITIONS
pages. Collections allow you to organize related dashboards together.
Available in: Intelligence
Create a Collection Reports Advanced
A collection contains your dashboard pages. After you create a collection, you can easily add
dashboard pages to create a cohesive and full display of your data.

95
Marketing Cloud Einstein and Analytics Dashboards

Manage a Collection
After you create a collection, you can edit the collection and its dashboard pages to fit your needs.

Create a Collection
A collection contains your dashboard pages. After you create a collection, you can easily add
EDITIONS
dashboard pages to create a cohesive and full display of your data.
1. From Analytics Builder, select Intelligence [Datorama] Reports. Available in: Intelligence
Reports Advanced
2. Select the Dashboards tab.
3. Click the down arrow next to Messaging & Journeys.
USER PERMISSIONS
4. Click Create Collection.
5. Name your collection, then add a description. To create a collection
• Create & Edit
6. Save your work.
Your collections appear on the left pane. After you click a collection, the associated dashboard
pages appear in the main screen.

Manage a Collection
After you create a collection, you can edit the collection and its dashboard pages to fit your needs.
EDITIONS
1. Click the collection you want to edit.
Available in: Intelligence
2. When you click the settings icon, these options appear:
Reports Advanced
• Rename — Renames the collection.
• Delete — Deletes the collection.
USER PERMISSIONS
• Duplicate — Creates a copy of the collection.
To manage a collection
3. When selecting a collection, the dashboard pages from the collection appear in the window • Create & Edit
below it. You can edit the dashboard page settings by clicking the dashboard page. These
options appear:
• Show Pages — Click to view the dashboard pages associated with your collection.
• Edit — Click to edit the dashboard page.
• Delete — Click to delete this dashboard page.
• Export — Click to export the dashboard page. The export formats available are:
– PDF
– PNG
– Excel
– PPT

• Update Dates — Click to update the date ranges for the selected dashboard page.
• Copy — Click to copy this dashboard page.

96
Marketing Cloud Einstein and Analytics Dashboards

Dashboard Pages
Dashboard pages segment your collections so you can divide up your data according to your
EDITIONS
preferences. Each page can be customized and filtered, so you can modify the design and remove
any unwanted data. Available in: Intelligence
Reports Advanced
Add a Dashboard Page to a Collection
After you create a collection, you can add dashboard pages to suit your specific reporting needs.
You can then add widgets to your dashboards to visualize and explore actionable insights.
Customize Dashboard Pages
Customizing your dashboard pages allows you to modify and focus on specific data in a view. You can apply filters and interactive
filtersets to your dashboards to get a better understanding of the data that appears on your dashboard.

Add a Dashboard Page to a Collection

After you create a collection, you can add dashboard pages to suit your specific reporting needs.
EDITIONS
You can then add widgets to your dashboards to visualize and explore actionable insights.

Note: You can create up to 50 dashboards in Intelligence Reports advanced. Available in: Intelligence
Reports Advanced
1. Click the collection you want to add a dashboard page to.
2. Click Add New. USER PERMISSIONS
3. To enter Edit mode, click the pencil icon. In edit mode you can customize and add widgets to
To add a dashboard page
your dashboard page. to a collection
• Create & Edit

Customize Dashboard Pages

Customizing your dashboard pages allows you to modify and focus on specific data in a view. You
EDITIONS
can apply filters and interactive filtersets to your dashboards to get a better understanding of the
data that appears on your dashboard. Available in: Intelligence
Reports Advanced
Dashboard Page Filters
You can apply filters to dashboard pages to limit or modify the data in a view. You can filter by
a dimension, measurement, or date dimension. Page level filters affect the page and the widgets on the filtered page. You can see
if there are any filters applied to your page from the filters tab.
Interactive FilterSet
Interactive filtersets enable you to save various configured views of your dashboard page by saving the selections made to the
interactive filter widgets. You can apply Filtersets as a filter option within the dashboard page.
Design Your Page
After you add a dashboard page to your collection, you can customize and design your page to create a visually appealing and
effective dashboard page.
Add Widgets to Dashboard Pages
After you create a collection, you can add dashboard pages to segment your data. You can then add widgets to your dashboards
to visualize and receive actionable insights.

97
Marketing Cloud Einstein and Analytics Dashboards

Create a Pivot Table from a Widget

Transform a widget into a pivot table to get insights on your data. You can customize the pivot table, apply filters, and even share
it with others.

Dashboard Page Filters

You can apply filters to dashboard pages to limit or modify the data in a view. You can filter by a
EDITIONS
dimension, measurement, or date dimension. Page level filters affect the page and the widgets on
the filtered page. You can see if there are any filters applied to your page from the filters tab. Available in: Intelligence
The two types of filters are: Reports Advanced
• Page Filters – Enable you to filter the page by a dimension, measurement, or date dimension.
• Interactive FilterSet – Enable you to save specific views of your dashboard page by saving the selections made to the interactive
filter widgets on the page.
Here’s a video about dashboard filters app:

Watch a video

Create a Dashboard Page Filter

You can apply filters to dashboard pages to limit or modify the data in a view. You can filter by a dimension, measurement, or date
dimension. Page level filters affect the page and the widgets on the filtered page.

Create a Dashboard Page Filter

You can apply filters to dashboard pages to limit or modify the data in a view. You can filter by a
EDITIONS
dimension, measurement, or date dimension. Page level filters affect the page and the widgets on
the filtered page. Available in: Intelligence
1. On the dashboard page, to enter edit mode, click the pencil icon. Reports Advanced
2. In the Edit Page pane on the left, click Page Filters. Here you can see if there are existing page
filters. USER PERMISSIONS
3. Click Add Filter.
To create, edit, and apply
You can add Dimension Filters, Measurement Filters, or both. filters
• Dimension Filters – Allow you to filter by the dimension values and apply the filter to the • Create & Edit
page. When applying multiple filters to one dimension, you must set an AND/OR conditional
operator to dictate the relationship between the different filters. When filtering by a
dimension, the two types of filters are:
– List filtering – The selected dimensions can be included or excluded in the filter:
• List of – Filter to include
• Not List of – Filter to exclude
From the dropdown, select the dimension values you want to filter by.

Note: You can apply only one List Filter per dimension. List Filters can be combined with multiple Conditional Filters.

• Measurement Filters – Allows you to filter by the value of the measurement and apply it to the page. For example, you want
to be able to see campaigns that have an Email Open Rate of over 75%. Measurement filters are conditional filters, and can only
have an ‘AND’ relationship with other filters, both in multiple measurement filters and within a single measurement filter.

98
Marketing Cloud Einstein and Analytics Dashboards

Available Filters — This table lists the available filtering options:

Type Operator Comments

Dimension > String/ Link/ Image/Video In When In or Not In is selected, a multi-select
control appears for the relevant values
Not In within the selected dimension.
Equals
Not Equals
Contains
Not Contains
Starts with
Ends with
Is Empty
Not Empty
Matches Either

Dimension > Date Before Open a date picker for the input field.

After

Measurement > Number/ Percentage/ > The input field has a label next to it
Currency according to the type of value (%, $ or any
>= other currency sign).
Dimension > Number <
Measurement > Duration <=
=
<>
Is NULL
Not NULL
Is NaN
Not NaN

Interactive FilterSet
Interactive filtersets enable you to save various configured views of your dashboard page by saving
EDITIONS
the selections made to the interactive filter widgets. You can apply Filtersets as a filter option within
the dashboard page. Available in: Intelligence
For example, if your dashboard page displays all campaigns around the world and you want to Reports Advanced
display the most successful campaigns in the US, you can save an interactive filterset. The filterset
loads the widgets in the dashboard page, displaying campaigns only in the US. After you create
the filterset, you can select the filterset, and the dashboard data loads automatically with the relevant data.

99
Marketing Cloud Einstein and Analytics Dashboards

Create an Interactive Filter

Interactive filtersets enable you to save various configured views of your dashboard page by saving the selections made to the
interactive filter widgets. You can apply filtersets as a filter option within the dashboard page.
Apply an Interactive Filterset to a Dashboard Page
After you create an Interactive filterset, any user with access to the dashboard page can apply the interactive filterset to the dashboard
page.

Create an Interactive Filter

Interactive filtersets enable you to save various configured views of your dashboard page by saving
EDITIONS
the selections made to the interactive filter widgets. You can apply filtersets as a filter option within
the dashboard page. Available in: Intelligence
1. To enter edit mode, click the pencil icon. Reports Advanced
2. Select the values in the interactive filter widgets that you want to save as an interactive filterset.
3. In the Edit page window, click + Interactive Filterset. USER PERMISSIONS
4. Name your interactive filterset. To create, edit, and apply
filters
5. To save the selections made to the interactive date widgets and interactive compare widgets
• Create & Edit
in the filterset, check the Save Date Interactive/Compare Widget dates in filtersets
checkbox. This checkbox enables the date range for the interactive widgets to be applied to
the interactive filterset.

Note: If you don’t select this checkbox, the dates selected within the interactive date widget and interactive compare widgets
aren’t applied to the filterset. The dashboard page’s default date range is displayed instead.

6. Save your filterset.

7. You can find the filtersets you created in the Edit Page window, under Interactive FilterSets.
8. To clear applied filtersets, click the option icon in the interactive filterset tab, and then click Clear Interactive Filters.
9. To delete a created filterset, select the filterset, and then click the bin icon.
All users can see created filtersets regardless of their user role and permissions. To clear selected interactive filtersets, open the options
menu when in edit mode and select Clear Interactive Filters.

Apply an Interactive Filterset to a Dashboard Page

After you create an Interactive filterset, any user with access to the dashboard page can apply the
EDITIONS
interactive filterset to the dashboard page.
1. Click the filter icon at the top of the dashboard page to open the Page Filters window. Available in: Intelligence
Reports Advanced
2. Under the Interactive FilterSet tab, select the interactive filterset you want to apply to the
dashboard page. All widgets that have interactive filters enabled on the dashboard page are
filtered according to the selected interactive filterset. USER PERMISSIONS
3. To see the details of the filterset, hover over the information icon next to the filterset name.
To create, edit, and apply
Note: If a widget is deleted from a filterset, the filterset still functions. To indicate that the filters
deleted widget is no longer being loaded as part of the filterset, it’s highlighted with red • Create & Edit
strikethrough text.

100
Marketing Cloud Einstein and Analytics Dashboards

Design Your Page

After you add a dashboard page to your collection, you can customize and design your page to
EDITIONS
create a visually appealing and effective dashboard page.
The three types of designs are: Available in: Intelligence
Reports Advanced
• Designed Themes – Ready-made, non-branded themes. When selecting a designed theme,
the InstaBrand toggles on, allowing you to further customize.
• InstaBrand – Branded themes that are automatically generated based on a logo or image that you uploaded.
• Custom Themes – A complete custom theme that you design from scratch.

Use Designed Themes

Designed themes provide an array of generic themes that you can apply to your dashboard page to produce stunning visualizations
of your data.
Use InstaBrand
InstaBrand is an AI-powered image analysis tool that automatically generates beautiful, branded dashboard page themes. You can
upload an image or choose from a catalog of images.
Custom Themes
Custom themes provide you with the flexibility to create any designed theme you want. After you apply an InstaBrand design, you
can apply manual changes to your dashboard page from the different customization options available beneath the InstaBrand
options.

Use Designed Themes

Designed themes provide an array of generic themes that you can apply to your dashboard page
EDITIONS
to produce stunning visualizations of your data.
1. In the dashboard page you want to customize, to enter edit mode, click the pencil icon. Available in: Intelligence
Reports Advanced
2. In the Edit page window, select the Design tab.
3. Under THEME, click the arrow to open the dropdown list, and then scroll down to LANDSCAPES.
You can see a list of ready-made themes to use. USER PERMISSIONS
4. Select the Landscape Theme you want to apply to your dashboard page, for example, Coastline. To create, edit, and apply
Your dashboard page automatically updates with the selected theme. filters
• Create & Edit
5. Save your dashboard page at the top right of the screen.

Use InstaBrand
InstaBrand is an AI-powered image analysis tool that automatically generates beautiful, branded
EDITIONS
dashboard page themes. You can upload an image or choose from a catalog of images.
1. To enter edit mode, click the pencil icon. Available in: Intelligence
Reports and Intelligence
2. In the edit page window, select the Design tab.
Reports Advanced
3. Toggle on the InstaBrand toggle.
4. In the Branding Assets section, these options are available: USER PERMISSIONS
• Logo – The logo is used in the dashboard page header along with the dashboard page
name. To open the Logo Options tab, click the plus icon from the logo. You can insert a To create, edit, and apply
filters
link to the logo or upload a file. Images must be under 50 MB.
• Create & Edit

101
Marketing Cloud Einstein and Analytics Dashboards

• Background Image – The background image is used as the dashboard page’s background. After you click the background
image, these options are available:
– Photos – In the search box, enter a keyword in the search box and hundreds of images display from the Unsplash library of
images.
– Link – Input a link to the logo you want to use as your background image.
– Upload File – Drag and drop a file or browse for the file you want to add as your background image.

5. Color Palette – To change the colors, select a color palette. InstaBrand automatically identifies the color palettes that exist in the
uploaded logo or image. You can fine-tune its colors as you want.
6. Fine-tune the InstaBrand display setting you want to apply to your dashboard page. These options are dynamic according to the
branding assets you set. The options are:
• Apply Color Palette to Charts – Selecting this checkbox applies the selected color palette to all the charts on the dashboard
page. If it isn’t selected, the chart color settings are based on the default or manual settings previously applied to the widget or
measurement list.
• Override Manual Color Changes – Selecting this checkbox overrides any manual color settings previously applied to the
widget’s settings in edit mode. This option is only available if you select the Apply Color Palette to Charts option.
• Show Image as Cover Image – Select this checkbox to apply the uploaded image as a background image to the dashboard
page. If you clear this checkbox, the image is hidden, but you can still use its color palette. This option is available if you uploaded
an image.
• Show Logo on Top – Select this checkbox to apply the uploaded logo to the header at the top of the dashboard page. If you
clear this checkbox, the logo is hidden, but you can still use its color palette. This option is available if you uploaded a logo.

7. Save your new theme after you finish configuring it.

8. Save your dashboard page at the top right of the screen.

Custom Themes
Custom themes provide you with the flexibility to create any designed theme you want. After you
EDITIONS
apply an InstaBrand design, you can apply manual changes to your dashboard page from the
different customization options available beneath the InstaBrand options. Available in: Intelligence
Note: Dashboard pages that have custom themes applied to them can’t be deleted. If you Reports Advanced
want to delete the dashboard page, apply a predefined theme, and then delete the dashboard
page.
• Layout – Customize the layout and design of your widgets along with the margins of the page.
• Background – Customize the dashboard page’s background color, background image, and opacity, and apply filters to control
brightness and contrast.
• Widgets – Modify your widget’s appearance, for example, fine-tune opacity to apply paddings.
• Fonts – Change the text style throughout your dashboard page.

Add Widgets to Dashboard Pages

After you create a collection, you can add dashboard pages to segment your data. You can then
EDITIONS
add widgets to your dashboards to visualize and receive actionable insights.
Available in: Intelligence
Create a Widget Reports Advanced
The widget creation process is streamlined so you can build your widget in just three steps.

102
Marketing Cloud Einstein and Analytics Dashboards

Add Data to Your Widget

You can add data to your widget by selecting the measurements and dimensions you want to display. This step is mandatory because
you can’t save the widget without data.
Apply a Filter to Your Widget
The Filters tab allows you to go over all the filters applied to the widget through the page, for example, date filters or top results.

Create a Widget
The widget creation process is streamlined so you can build your widget in just three steps.
EDITIONS
• Data (mandatory)
• Filter (optional) Available in: Intelligence
Reports Advanced
• Design (optional)
1. On the page you want to add a widget to, to enter edit mode, click the pencil icon.
USER PERMISSIONS
2. To add a widget, click the + icon from the top toolbar.
To create, edit, and apply
3. From the Edit Widget window on the left, select the type of widget you want to create. All
filters
widget types are divided into categories. You can search through the category or use the Search
• Create & Edit
option to search for a specific widget.
4. To view the full list of available widget types, click More Types.
5. After you select a widget type, add a name. Name your widget so you can use other features later. If you want to use filters, make
sure that you use the same names.
6. To show or hide the widget title, click the eye icon next to the widget name.

Add Data to Your Widget

You can add data to your widget by selecting the measurements and dimensions you want to
EDITIONS
display. This step is mandatory because you can’t save the widget without data.
Intelligence Reports has icons for measurements and dimensions to help you easily recognize and Available in: Intelligence
select the entities you’re looking for. Reports Advanced

Measurements
USER PERMISSIONS

To create, edit, and apply

filters
Dimensions • Create & Edit

Dates

Filtered Measurements

103
Marketing Cloud Einstein and Analytics Dashboards

Calculated measurements and dimensions

1. In edit mode, select the widget you’re adding data to.

2. Make sure that you’re in the Data tab.
3. If you’re adding data to a new widget, click the plus (+) icon and add the data.
4. If you’re adding data to an existing widget, click the plus (+) icon in the Fields section.

Note:
• By default, Intelligence Reports enables the suggested quick filter and suggests fields based on the fields you have in other
widgets on the page. You can use these suggestions or select your own measurements or dimensions. To disable the
suggestions, click Suggestion.
• If the max number of allowed measurements or dimensions are already added to the widget, you must remove the existing
entity, and only then add the new dimension or measurement.

5. Select the measurements or dimensions you want to display in your widget. Your data is added to the widget automatically, and it
updates in real time.
6. To add customized dimensions and measurements, Click Add Calculated Fields. You can also create and manage your calculated
fields in the Setup tab.
7. Save your widget.
8. Add filters and design your widget.

Apply a Filter to Your Widget

The Filters tab allows you to go over all the filters applied to the widget through the page, for
EDITIONS
example, date filters or top results.
To modify a filter, click it. Available in: Intelligence
Reports Advanced
1. From the widget you want to apply a filter to, make sure that you’re in edit mode.
2. Select the Filters tab.
USER PERMISSIONS
3. To add a filter, click the plus (+) icon. You can add Dimension Filters, Measurement Filters, or
both: To create, edit, and apply
filters
• Dimension Filters – Allow you to filter by the dimension values and apply the filter to the
• Create & Edit
page. When filtering by a dimension, the two types of filters are:
• List filtering – The selected dimensions can be included or excluded in the filter:
– List of – Filter to include
– Not List of – Filter to exclude

Select the dimension values you want to filter by from the dropdown. You can apply only one List Filter per dimension. List Filters
can be combined with multiple Conditional Filters.
Conditional filtering – Filter using logical conditions applied to Dimension values.
• Equals
• Not Equal
• Contains

104
Marketing Cloud Einstein and Analytics Dashboards

• Not contains
Select the function you want to filter by, and add the condition. You can apply Multiple Conditional Filters to a Dimension.

4. To edit a filter, click the pencil icon on the filter, and edit as needed.

Create a Pivot Table from a Widget

Transform a widget into a pivot table to get insights on your data. You can customize the pivot
EDITIONS
table, apply filters, and even share it with others.
1. In Analytics Builder, select Intelligence Reports. Available in: Intelligence
Reports and Intelligence
2. On the Dashboards tab, select the widget that you want to convert to a pivot table.
Reports Advanced
3. Click the Options icon and select Explore in Pivot Table.

USER PERMISSIONS

To create a pivot table from

a widget:
• Create & Edit

You’re redirected to the Pivot Tables tab, and the data now appears in a pivot table.

105
Marketing Cloud Einstein and Analytics Dashboards

SEE ALSO:
Create a Pivot Table in Intelligence Reports

Apply Filters to Dashboards

Filters enable you to focus on the data most relevant to you. When you select a filter in a dashboard,
EDITIONS
it applies to all dashboards.
To clear a filter, from the options menu at the top right, select Clear User Filters Cache. Available in: Intelligence
Reports and Intelligence
To apply filters to the dashboard, select the filters, and click Apply.
Reports Advanced
Note: If you don’t see this option, make sure that you have the correct user permission.

These filters are available: USER PERMISSIONS

• Send Date – The date the email or message was sent. In some dashboards you can filter the To access dashboards
send date by: • Access, View & Export /
Schedule / “Create &
– Current – The current date includes emails or messages sent within the selected timeframe,
Edit”
even if the emails or messages were opened after the selected timeframe. For example, if
you set the time period to the month of October and sent an email on October 25 that
wasn’t opened until November 2, the email is still included in the current time period.
– Compare to – Identifies the timeframe you want to compare to. The comparison period shows whether the amount increased
or decreased, by how much, and the percentage change.

• Business Unit – Filters dashboards by business unit. This filter is available only if you have permissions and are logged into the
enterprise business account (the parent account).

Note: You can filter the data by more than one selection.

106
Marketing Cloud Einstein and Analytics Dashboards

• Campaign – Filters dashboards by campaign. This filter is available only if you assign a campaign to your emails in Marketing Cloud.
• Email Name – Filters dashboards by a specific email name.
• Email Subject – Filters dashboards by a specific email subject
• Journey Name – Filters dashboards by a specific journey name. (Only available if you have Journey Builder enabled in your account.)
• Journey Version – Filters dashboards by a specific journey version. (Only available if you have Journey Builder enabled in your
account.)
• Journey Activity Name – Filters dashboards by a specific journey activity name. (Only available if you have Journey Builder enabled
in your account.)
• Mobile App – Filters dashboards by a specific mobile app. This is the app name that the message was sent to.
• Mobile OS – Filters the dashboards by a specific mobile operating system, for example, Android or iOS.
• Push Send Name – Filters the dashboards by the name of the push message that was sent.
• Push Send Title – Filters the dashboards by the title used in the message content shown to the end user.

Sharing Dashboard Pages and Widgets

Slack provides seamless collaboration with colleagues and clients. Marketing teams can work
EDITIONS
together and communicate on campaigns and improve cross-functional work. You can share
dashboards and widgets via Slack, email, or as downloaded local files. You can also schedule when Available in: Intelligence
to share reports. Reports and Intelligence
Reports Advanced
Sharing Dashboard Pages and Widgets via Intelligence Reports Insights for Slack
Utilize Intelligence Reports insights for Slack to share dashboard pages and widgets.
Share Dashboard Pages and Widgets via Email
You can share widgets and pages via email to collaborate with colleagues and clients.
Download Dashboard Pages and Widgets
You can download dashboard pages and widgets in a variety of formats to your device.
Schedule Reports for Dashboard Pages and Widgets
You can schedule to receive reports of your dashboard page or widget as a PNG or PDF file. Filters aren’t applied to scheduled reports.

Sharing Dashboard Pages and Widgets via Intelligence Reports Insights for Slack
Utilize Intelligence Reports insights for Slack to share dashboard pages and widgets.
EDITIONS

Integrate Insights for Slack and Intelligence Reports Available in: Intelligence
Integrate with Intelligence Reports Insights for Slack to share dashboard pages and widgets. Reports and Intelligence
You can configure the integration on the business unit or collection level. Users with permissions Reports Advanced
and access to the business unit or collection can then share dashboard pages and widgets in
Slack.
Share Dashboard Pages and Widgets via Slack
In order to share your dashboard pages and widgets through Slack you need to set up your Intelligence Reports Insights for Slack
Integration in the Setup tab. After you set up the integration you can track and monitor your campaigns and collaborate with Slack.
Slack is permission based, only users with permissions and access to the business unit or collection can share dashboard pages and
widgets.

107
Marketing Cloud Einstein and Analytics Dashboards

Integrate Insights for Slack and Intelligence Reports

Integrate with Intelligence Reports Insights for Slack to share dashboard pages and widgets. You
EDITIONS
can configure the integration on the business unit or collection level. Users with permissions and
access to the business unit or collection can then share dashboard pages and widgets in Slack. Available in: Intelligence
To integrate Intelligence Reports Insights for Slack with Intelligence Reports for Engagement, you Reports and Intelligence
install an incoming webhook app. You can use a single webhook and share charts to any public Reports Advanced
Slack channel. You can also predefine a list of channels and associate a webhook per channel. The
advantage of using a webhook per channel is that you can configure both public and private USER PERMISSIONS
channels.
1. On the Setup tab, click Integrations. To integrate Slack:
• Create & Edit
2. Turn on Slack if it’s turned off.
3. Choose whether to integrate the entire business unit or a collection.
4. Enter an integration name that you can easily distinguish.
5. If you’re integrating Slack at the collection level, select the collections from the Target Collection dropdown.
6. Select the type of webhook to use.
• Single Webhook—Share to any public channel.
• Webhook per Channel—Share to both public and private channels.

7. Add the webhook link. If you don’t have the webhook link, click Get Slack Webhook, which redirects you to Slack.
8. Save your work.

Share Dashboard Pages and Widgets via Slack

In order to share your dashboard pages and widgets through Slack you need to set up your
EDITIONS
Intelligence Reports Insights for Slack Integration in the Setup tab. After you set up the integration
you can track and monitor your campaigns and collaborate with Slack. Slack is permission based, Available in: Intelligence
only users with permissions and access to the business unit or collection can share dashboard pages Reports and Intelligence
and widgets. Reports Advanced
1. Select the dashboard page or widget that you want to share.
2. Click Share, and then click Slack. USER PERMISSIONS
Note: You can’t share to a private channel or by direct messaging. To share dashboard pages
and widgets in Slack:
• Access, View & Export,
Schedule, Create & Edit

108
Marketing Cloud Einstein and Analytics Dashboards

Enter the Slack channel (1), and enter a message that describes what you’re sharing (2). To send the message with a predefined
name, select Send as (3). This option appears only when defined in the configuration settings. Preview what you’re sending (4).

3. Click Share.

Note: If your message fails, make sure that the channel name is correct. In the notification, click Edit settings and enter the
correct name.

109
Marketing Cloud Einstein and Analytics Dashboards

Share Dashboard Pages and Widgets via Email

You can share widgets and pages via email to collaborate with colleagues and clients.
EDITIONS
1. Select the dashboard page or widget that you want to share.
Available in: Intelligence
2. Click Share, and then click Email.
Reports and Intelligence
Reports Advanced

USER PERMISSIONS

To share dashboard pages

and widgets in email:
• Access, View & Export,
Schedule, Create & Edit

Enter the recipient’s email address (1), and select the format (2). Enter the subject (3). The name of the dashboard or page is used
by default. Preview what you’re sending (4).

110
Marketing Cloud Einstein and Analytics Pivot Tables Overview

3. Click Send.

Download Dashboard Pages and Widgets

You can download dashboard pages and widgets in a variety of formats to your device.
EDITIONS
1. Go to the dashboard page or widget that you want to download.
Available in: Intelligence
2. Click the Share icon.
Reports and Intelligence
3. Click Download. Reports Advanced
4. Select the format.
• When exporting to PowerPoint, Intelligence Reports splits long pages into multiple slides USER PERMISSIONS
according to the slide height and the margin width at the top and bottom.
To download dashboard
• When exporting to Excel, Intelligence Reports splits each widget on the dashboard page pages and widgets:
into individual tabs within the spreadsheet. • Access, View & Export,
Schedule, Create & Edit
5. Click Download Now.

Schedule Reports for Dashboard Pages and Widgets

You can schedule to receive reports of your dashboard page or widget as a PNG or PDF file. Filters
EDITIONS
aren’t applied to scheduled reports.
1. Go to the dashboard page or widget that you want to schedule. Available in: Intelligence
Reports and Intelligence
2. Click the Share icon.
Reports Advanced
3. Click Scheduled Reports. You’re redirected to the Reports tab, and a report is created based
on the format that you selected.
USER PERMISSIONS
4. To change the format, click the Export Format dropdown list. You can export dashboard pages
to PNG or PDF. You can export widgets to PNG. To create a scheduled report
of dashboard pages or
5. Select when to send the report and how.
widgets:
6. Save your settings, or to run the report now, click Save & Run. • Access, View & Export,
Schedule, Create & Edit
SEE ALSO:
Set Report Schedule and Delivery Method

Pivot Tables Overview

Pivot tables allow you to explore your data from multiple perspectives. You can calculate, summarize,
EDITIONS
and analyze data by seeing comparisons, patterns, and trends in your data. With pivot tables, you
can create custom reports without the need for query formulas, such as SQL queries. Available in: Intelligence
For a detailed explanation of the metrics featured in pivot tables, see Dimensions and Measurements. Reports and Intelligence
Reports Advanced
For more information about pivot tables, click these links:

Note: Emails configured to Suppress from Send Reports aren't included in Intelligence
Reports.

111
Marketing Cloud Einstein and Analytics Pivot Tables Overview

Out-of-the-Box Pivot Table Examples

By default, Intelligence Reports for Engagement comes with five out-of-the-box pivot table examples. These examples help you get
started so you can see how the most common pivot tables are configured and set up. You can use them as is, copy and then adjust
them, or even delete them if they‘re not required.
Create a Pivot Table in Intelligence Reports
Use a pivot table to explore and extract data. For example, you can get sends and open rates for all your emails to see how well a
specific email performed. You can also export a pivot table locally or use it to create a scheduled report.
Customize a Pivot Table in Intelligence Reports
You can change the data that is displayed in a pivot table, show or hide columns, and make other customizations.
Export a Pivot Table in Intelligence Reports
You can export a pivot table as a report and run it as part of a workflow in real time or on a defined schedule. You can also export
to an Excel file, for example, and share it with others.
Manage Pivot Tables in Intelligence Reports
You can manage pivot tables in Intelligence Reports for Engagement after you create them. You can edit, duplicate, and delete
existing pivot tables.
Apply Filters to a Pivot Table
Add filters to a pivot table to narrow down the data and focus on what’s relevant to your use case. For example, add a filter to focus
on a specific email name instead of all the emails in the campaign. Or filter by a campaign name to focus on that campaign.

Out-of-the-Box Pivot Table Examples

By default, Intelligence Reports for Engagement comes with five out-of-the-box pivot table examples.
EDITIONS
These examples help you get started so you can see how the most common pivot tables are
configured and set up. You can use them as is, copy and then adjust them, or even delete them if Available in: Intelligence
they‘re not required. Reports and Intelligence
These examples are available: Reports Advanced

• Email Daily Send Summary — Summarizes your email send data so you can see how many
emails were sent, delivered, and bounced for a specific time period.
• Best Performing Send Day — Shows the send day that has the highest open rate, click to open rate, and email opens.
• Audience Engagement Over Time — See how your audience engaged with your emails by looking at email clicks for all your
campaigns.
• Campaign Performance — See your overall campaign performance for each campaign and email.
• Journey Performance - See your overall journey performance by looking at journey name, version and activity.

112
Marketing Cloud Einstein and Analytics Pivot Tables Overview

Create a Pivot Table in Intelligence Reports

Use a pivot table to explore and extract data. For example, you can get sends and open rates for all
EDITIONS
your emails to see how well a specific email performed. You can also export a pivot table locally or
use it to create a scheduled report. Available in: Intelligence
You can also create a pivot table directly from a widget in the Dashboards tab. For more information, Reports and Intelligence
see Create a Pivot Table from a Widget. Reports Advanced

1. In Analytics Builder, select Intelligence Reports.

2. On the Pivot Tables tab, click Create Pivot Table. USER PERMISSIONS
3. To add data to the pivot table, click + Add a Field. To create or export pivot
tables
• Access, View & Export,
Schedule, Create & Edit
To save, edit, and delete
pivot tables
• Create & Edit

When adding data, Dimensions are always placed in Rows or Columns, while Measurements are always placed in Values. The pivot
table changes as you add or remove data.

4. When you’re done adding data, close the Add Data window.
5. In the Pivot Table Settings window, set the date range for the data that you want to view.
6. To apply a filter, in the Filters section, click the + icon and set your filters.
You can also apply a filter inside the pivot table in the column header.

7. If you have Intelligence Reports Advanced, you can create and edit calculated fields by clicking the Add Calculated Field icon. For
more information, see Add Data to Your Widget .

113
Marketing Cloud Einstein and Analytics Pivot Tables Overview

8. Name the pivot table.

9. To visualize your data in a chart, turn on Visualize.

• To show specific dimensions and measurements, or to change the display, click Chart Settings (1).
• To change how the results are sorted, click Chart Top and Sorting (2).
• To view the pivot table as a flat table, click the flat table icon (3).

10. To save, export, or download your pivot table, click More Actions.
11. Save your work.
The new pivot table appears in the Pivot Tables list, and you can edit, delete, and export it.

Customize a Pivot Table in Intelligence Reports

You can change the data that is displayed in a pivot table, show or hide columns, and make other
EDITIONS
customizations.
1. In Analytics Builder, select Intelligence Reports. Available in: Intelligence
Reports and Intelligence
2. On the Pivots Tables tab, select the pivot table that you want to change and click Edit.
Reports Advanced
3. To hide a dimension or measurement, in the Pivot Table Settings window, hover over the field
name and click the eye icon.
USER PERMISSIONS
4. To delete a field, click X.
5. To add or change data, click the + icon. To save, edit, and delete
pivot tables
6. To hide the column or row totals in the pivot table, click Options next to Columns or Rows • Create & Edit
and deselect the checkbox.

114
Marketing Cloud Einstein and Analytics Pivot Tables Overview

Export a Pivot Table in Intelligence Reports

You can export a pivot table as a report and run it as part of a workflow in real time or on a defined
EDITIONS
schedule. You can also export to an Excel file, for example, and share it with others.
1. In Analytics Builder, select Intelligence Reports. Available in: Intelligence
Reports and Intelligence
2. On the Pivot Tables tab, select the pivot table.
Reports Advanced
3. Click More Actions and then select the export option.
• Schedule Export — If you want to export to a report with a defined schedule, for example USER PERMISSIONS
create a report every Monday at 8 AM, you have two options. When you select an option,
the report format and options change according to the selected format. To schedule an export:
– Pivot Table (Excel) — Exports the pivot table to an Excel file as a pivot table object • Schedule/ Create & Edit
without including the totals.
– Flat Table — Creates a report in an Excel format.

• Export — If you want to export to a flat file, you have two options:
– Pivot Table (As Is) — Exports the pivot table to an Excel file as is.
– Flat Table — Exports the pivot table to an Excel file as a flat table.

SEE ALSO:
Create a Flat Table Report
User Roles and Permissions in Intelligence Reports

Manage Pivot Tables in Intelligence Reports

You can manage pivot tables in Intelligence Reports for Engagement after you create them. You
EDITIONS
can edit, duplicate, and delete existing pivot tables.
The pivot tables list contains the following information: Available in: Intelligence
Reports and Intelligence
Column Description Reports Advanced

ID The ID of the pivot table. This ID is generated

automatically. USER PERMISSIONS

Name The name of the pivot table. To create or export pivot

tables
Created By The name of the user who created the pivot • Access, View & Export /
table. Schedule / Create & Edit
Created On The date and time the pivot table was created. To save, edit and delete
pivot tables
Last Update By The user who made the last update. • Create & Edit
Last Update On The date and time the last update was made to
the pivot table.

From here, you can perform the following actions:

• Edit — If you want to change a pivot table, for example, change the dimensions and measurements.

115
Marketing Cloud Einstein and Analytics Pivot Tables Overview

• Duplicate — If you want to create a copy of a pivot table to change it.

• Delete — If you want to delete a pivot table.

Note: When you delete a pivot table, it goes to your workspace bin. If for some reason you want to restore a pivot table,
contact support.

SEE ALSO:
Create a Flat Table Report
User Roles and Permissions in Intelligence Reports

Apply Filters to a Pivot Table

Add filters to a pivot table to narrow down the data and focus on what’s relevant to your use case.
EDITIONS
For example, add a filter to focus on a specific email name instead of all the emails in the campaign.
Or filter by a campaign name to focus on that campaign. Available in: Intelligence
Let’s see how to set up a filter for the following scenario: you want to see data only for campaigns Reports and Intelligence
that contains the words ‘Welcome’ or ‘Birthday’, and whose bounce rate was greater than 60%. Reports Advanced

1. Go to Analytics Builder, select Intelligence Reports.

2. On the Pivot Tables tab, select the table that you want to apply a filter to. USER PERMISSIONS
3. In the Pivot Table Settings window, under Add Filters, click the + icon. To apply filters to pivot
tables:
4. You can also add a filter directly from the column header.
• Create & Edit
5. Search for the dimension or measurement that you want to filter by, for example, Campaign.
6. Use the operators to specify how you want to filter. For our example, select Contains and enter
the value Welcome.
7. To add another condition, click +Condition. For example, enter Birthday.
8. To apply both conditions, use an AND statement. If you want to filter for campaigns that contain either word, use an OR statement.

116
Marketing Cloud Einstein and Analytics Pivot Tables Overview

9. To add another filter, click +Add New Filter.

For example, select Email Bounce Rate, set the operator to Greater Than, and enter 60%.

117
Marketing Cloud Einstein and Analytics Pivot Tables Overview

10. Save your work.

Here you can see that the filter was set up correctly.

118
Marketing Cloud Einstein and Analytics Reports Overview

Tip: To add a filter to exclude test emails, search for the Test Email Indicator dimension, and set it to False.

Reports Overview
Reports are an easy way to retrieve, view, and share a detailed analysis of your data. You can create
EDITIONS
the report from scratch by going to the Reports tab and clicking Create New Report. Or you can
create the same report by using the Schedule Export option when in a dashboard page or in a pivot Available in: Intelligence
table. For example, to create a flat table report, create the report from scratch in Excel, or go to a Reports and Intelligence
predefined pivot table and use the Schedule Export Flat Table option. Reports Advanced
Emails configured to Suppress from Send Reports aren't included in Intelligence Reports. For a
detailed explanation of the metrics featured in each report, see Dimensions and Measurements.
If a report fails after more than 7 consecutive times, the report is disabled. It’s advised that you check out why the report failed. Go to
the Report’s history to see what caused the report to fail. After you fix the report, re-enable it so that it runs again. For more information,
see View Report History.
You can also schedule how and when you want the report to run. For example, you can run the report every day at a specific hour. While
configuring your report’s scheduling, you can define the frequency and delivery time of the report, and the delivery method.
These delivery methods are supported:
• AzureBlob
• Email
• FTPS
• Google Drive
• HDFS
• SFTP
• AWS - S3
• Google Cloud Storage

Create a Report
You can create a report when you want to retrieve, view, and share a detailed analysis of your data. You can create a report from
scratch or export an entity like a pivot table or dashboard page to a scheduled report.
Set Report Schedule and Delivery Method
You define scheduling and delivery methods for a report to decide how you want to run and share it. As a result, you decide when
the report is sent. For example, if you want the report to go out every day at a specific time, you can set a daily frequency and the
time, say, 10:00 PM. You can also define how you want the report to be executed and shared.
Manage Reports
After you create a report, it appears in your reports list. From your reports list, you can view all your reports, edit, delete, and create
a copy.
View Report History
You can use the report history to monitor your reports. The report history log displays a list of all the times the report ran. And it
provides information about each report execution, such as whether the run was successful and the start and end dates of the
execution. You can also download report outputs.

119
Marketing Cloud Einstein and Analytics Reports Overview

Report Settings
You can set your report settings to allow or prevent users from receiving a download link for large attachments. In Intelligence
Reports for Engagement, large files—over 7 MB—are shared via a download link. Any user with the download link can download
the report.
Apply Filters to a Report
Add filters to a report to narrow down the data that you see in reports and focus on what’s relevant to your use case. You can filter
by a standard or custom dimension, such as a campaign, email domain, or country, or by a custom measurement, such as an email
bounce rate over 60%.

Create a Report
You can create a report when you want to retrieve, view, and share a detailed analysis of your data.
EDITIONS
You can create a report from scratch or export an entity like a pivot table or dashboard page to a
scheduled report. Available in: Intelligence
Reports in Intelligence Reports can be in these formats: Reports and Intelligence
Reports Advanced
• Flat Table (Excel/CSV) — Creates a flat file with the data. For example, display the total number
of sends per send date.
• Pivot Table (XLS) — Creates an Excel in the same structure as your pivot table view.
• Dashboard (PDF) — Exports a dashboard into a PDF.
For more information about how to create different reports, click these links:

Create a Flat Table Report

You can create a flat table report when you want a report that extracts your raw data into a CSV or Excel file.
Create a Pivot Table Report
To export a report to an Excel file or display the data in a pivot table, you create a pivot table. The pivot table isn't a real Excel object,
rather it appears only in the form of a pivot table. You can also create a pivot table report by exporting a pivot table to a scheduled
report.
Create a Dashboard Report
You can create a dashboard report in PDF format. You can also create a dashboard report by exporting a dashboard page. When
creating the report from scratch, you must link to a dashboard page. The configuration settings come from the dashboard page, so
any changes made to the source affect the configuration settings of the report later on.

SEE ALSO:
User Roles and Permissions in Intelligence Reports

120
Marketing Cloud Einstein and Analytics Reports Overview

Create a Flat Table Report

You can create a flat table report when you want a report that extracts your raw data into a CSV or
EDITIONS
Excel file.
1. From Analytics Builder select Intelligence [Datorama] Reports. Available in: Intelligence
Reports and Intelligence
2. Select the Reports tab.
Reports Advanced
3. Click Create New Report.

Note: You can also create the same report from the Pivot Table module by using schedule USER PERMISSIONS
export as a flat table.
To create and edit reports
4. Define your General details. • Schedule / “Create &
Edit”
a. Enter a Name.
b. Select the Export Format: CSV or Excel.

Note: The configuration settings change according to the format type you select. For example, if you select CSV, not all
the fields are available.

5. Define your Configuration details:

a. To determine the dates you want to pull data from, select the Time Period. You can use a predefined time period, such as week,
month, or year, or you can define a custom date.
b. In Measurements, select the measurements you want pulled into the report, for example, email sends. You can select up to
100 measurements.
c. In Dimensions, select the dimensions you want pulled into your report, for example, send date. You can select up to 80
dimensions.

Note: For a detailed explanation of the metrics available, see Dimensions and Measurements.

6. Customize your report in the Configuration settings area:

a. To include the total numbers in the report, select the Show Totals checkbox.
b. From the Sort By dropdown, search for and choose the dimension or measurement you want to sort the report by. You can
choose from any of the selected dimensions or measurements.
c. From the Sort Order dropdown, select the way you want to sort, either descending or ascending order.
d. To add another filter to your report, click Add Filter. For example, you can also filter by Campaign Name. For more information
about filters, refer to Apply Filters.

7. Define scheduling and delivery methods for the report. Refer to Define Scheduling and Delivery Methods.

SEE ALSO:
User Roles and Permissions in Intelligence Reports

121
Marketing Cloud Einstein and Analytics Reports Overview

Create a Pivot Table Report

To export a report to an Excel file or display the data in a pivot table, you create a pivot table. The
EDITIONS
pivot table isn't a real Excel object, rather it appears only in the form of a pivot table. You can also
create a pivot table report by exporting a pivot table to a scheduled report. Available in: Intelligence
When creating the report from scratch, you must link to an existing pivot table. The configuration Reports and Intelligence
settings come from the pivot table, so any changes made to the source affect the configuration Reports Advanced
settings of the report later on.

Note: Most of the report configuration settings are self-explanatory or have a tooltip available USER PERMISSIONS
in the platform.
To create and edit reports
1. Access the Intelligence Reports for Engagement, select the Reports tab. • Schedule / “Create &
2. Select the Reports tab. Edit”

3. Click Create New Report.

Note: When creating the report from scratch, you must link to an existing pivot table. The configuration settings come from
the pivot table, so any changes made to the source affect the configuration settings of the report later on.

4. For General details, name the report and select Export Format: Pivot Table.
5. To define your report configuration details, select the time period from which to pull data.
6. Specify when and how to deliver the report.

SEE ALSO:
User Roles and Permissions in Intelligence Reports
Set Report Schedule and Delivery Method

Create a Dashboard Report

You can create a dashboard report in PDF format. You can also create a dashboard report by
EDITIONS
exporting a dashboard page. When creating the report from scratch, you must link to a dashboard
page. The configuration settings come from the dashboard page, so any changes made to the Available in: Intelligence
source affect the configuration settings of the report later on. Reports and Intelligence
1. From Analytics Builder, select Intelligence [Datorama] Reports. Reports Advanced

2. Select the Reports tab.

3. Click Create New Report. USER PERMISSIONS
4. Define your General details. To create and edit reports
a. Enter a Name. • Schedule / “Create &
Edit”
b. Select the Export Format: PDF.
c. To determine how long reports are kept before they’re deleted, enter the Purge Report
History (Days). For example, if you enter 30, all reports are deleted after 30 days.

Note: By default, the number of days is set to 180, which is also the maximum number of days you can keep reports.

5. Define your Configuration details, and select the dashboard page for which you’re creating the report.

122
Marketing Cloud Einstein and Analytics Reports Overview

6. Define scheduling and delivery methods for the report. Refer to Define Scheduling and Delivery Methods.

SEE ALSO:
User Roles and Permissions in Intelligence Reports

Set Report Schedule and Delivery Method

You define scheduling and delivery methods for a report to decide how you want to run and share
EDITIONS
it. As a result, you decide when the report is sent. For example, if you want the report to go out
every day at a specific time, you can set a daily frequency and the time, say, 10:00 PM. You can also Available in: Intelligence
define how you want the report to be executed and shared. Reports and Intelligence
The following delivery methods are supported: Reports Advanced

• AzureBlob
• Email USER PERMISSIONS
• FTPS To create and edit reports
• Google Drive • Schedule
• HDFS
• SFTP
• AWS - S3
• Google Cloud Storage
When a report is executed according to a scheduled time, it’s known as a scheduler. You can set up multiple schedulers per report,
depending on your needs. For example, you can send a report to the management team on a weekly basis and the same report to the
analyst team daily. You can also share the report via Email and FTPS simply by adding FTPS as a delivery method and updating the
scheduler.
1. When defining a report, go to the Report Scheduling area.
2. Select the Active checkbox. After you select this checkbox, all options are enabled.
3. Select how frequently you want the report to be sent from the Frequency dropdown. More settings are added based on the
frequency you select. For example, if you select daily, you can set how many times a day the report is sent. If you select weekly, you
can also set the day of the week and time.
4. In Delivery Hour, enter the exact hour you want the report to be sent.

Note: If you want to use an automatic hour instead of defining your own hour, select Automatic. By default, automatic is
defined as 6:00 UTC.

5. In the Delivery Method dropdown in the Connection Info area, select how you want the report to be exported and shared. For
example, select Email.

Note: More settings are available depending on the delivery method you select. For example, if you select Email, you can
enter the recipients’ email addresses. If you select FTPS, you can enter the FTPS details.

6. To apply this scheduler to your report, click Add As New Scheduler.

Note: If you don’t complete this step, then your report can’t run on a schedule.

123
Marketing Cloud Einstein and Analytics Reports Overview

7. To create a scheduler using the same configuration, for example, if you also want to share the report via FTPS, change the delivery
method to FTPS. Then fill in any necessary settings, and click Add As New Scheduler. After you complete this step, a new row is
added to the table.
8. To change a scheduler and override the settings, select the row of the scheduler, and make your changes, for example, change the
delivery hour. Then click Update Scheduler.
9. After you define your report and schedulers, click Save and Run, or to save the settings and not run the report, click Save.

SEE ALSO:
User Roles and Permissions in Intelligence Reports

Manage Reports
After you create a report, it appears in your reports list. From your reports list, you can view all your
EDITIONS
reports, edit, delete, and create a copy.
If you want to make changes to a report, click Edit. For example, change the delivery hour. Available in: Intelligence
Reports and Intelligence
If you want to create a copy of a report and make changes to it, click Duplicate. You can duplicate
Reports Advanced
the reports with or without the schedulers.
If a report is no longer needed, click Delete. When you delete a report, it goes to your workspace
bin. If you want to restore a deleted report, contact support.
To run the report immediately, click Run Now.
To process the reports and split the data into files by date, click Batch Process. Batch processing doesn’t affect the original report
configuration.

Note: If a report fails after more than 7 consecutive times, the report is disabled. It’s advised that you check out why the report
failed. Go to the Report’s history to see what caused the report to fail. After you fix the report, re-enable it so that it runs again. For
more information, see View Report History.
The reports list contains the following information:

Column Description
ID The ID of the report. This ID is generated automatically.

Name The name of the report.

Format The report’s export format, which is given during the report’s
creation.

Scheduling Status Indicates if the report’s scheduling is enabled or disabled. If the

report is disabled, it’s currently not running.

Next Report Date Displays the date of the next report to run.

Created By The name of the user who created the report.

Created On The date and time the report was created.

Last Update By The user who made the last update.

124
Marketing Cloud Einstein and Analytics Reports Overview

Column Description
Last Update On The date and time the last update was made to the report.

SEE ALSO:
User Roles and Permissions in Intelligence Reports

View Report History

You can use the report history to monitor your reports. The report history log displays a list of all
EDITIONS
the times the report ran. And it provides information about each report execution, such as whether
the run was successful and the start and end dates of the execution. You can also download report Available in: Intelligence
outputs. Reports and Intelligence
1. Select the Reports tab. Reports Advanced

2. Select a report, and then click History. A list appears with all the report executions. Each time
a report runs, a new job is executed and a new row appears in the list. USER PERMISSIONS
3. If you want to perform actions on a specific log, select the row of the log. To create and edit reports
4. Perform one of the following: • Schedule / “Create &
Edit”
• Edit — To edit the report’s configuration settings.
• Delete — To delete a log from the list.
• Refresh — To refresh the history log, which can be useful if you ran a report and the status changed.
• Download — To download the report output.
• Run Now — To run the same report again.
• Rerun Now — To run the same job again.

To get more information on report execution, use the following link:

Review Report Execution Information in Intelligence Reports

When a report runs in Intelligence Reports for Engagement, you can see a list of all the report executions. Each time a report runs,
a new job is executed and a new row appears in the list.

Review Report Execution Information in Intelligence Reports

When a report runs in Intelligence Reports for Engagement, you can see a list of all the report
EDITIONS
executions. Each time a report runs, a new job is executed and a new row appears in the list.
You can see the following information: Available in: Intelligence
Reports and Intelligence
Column Description Reports Advanced

Job ID A system-generated ID.

Start Date The starting date the data was queried. This date is defined when configuring
the report.

End Date The ending date the data was queried. This date is defined when configuring
the report.

125
Marketing Cloud Einstein and Analytics Reports Overview

Column Description
Source The location where the job was triggered from, for example, manual.

Format The export format of the report, either PDF or Excel. The format is defined when configuring the report.

Method The delivery method, such as Email or FTP. The method is defined when configuring the report.

Reason If the job fails, the report history includes a reason, for example, query validation.

Execution Start Date The start time the job was executed.

Execution End Date The end time the job was executed.

User The name of the user who created the report.

Report Settings
You can set your report settings to allow or prevent users from receiving a download link for large
EDITIONS
attachments. In Intelligence Reports for Engagement, large files—over 7 MB—are shared via a
download link. Any user with the download link can download the report. Available in: Intelligence
To control your report settings for large files: Reports and Intelligence
Reports Advanced
1. From the Analytics Builder, select Intelligence [Datorama] Reports.
2. Select the Setup tab and click Report Settings.
3. By default, the Allow Download of Large Attachments toggle is enabled. To prevent a download link of your report from being
sent, disable the toggle.

Apply Filters to a Report

Add filters to a report to narrow down the data that you see in reports and focus on what’s relevant
EDITIONS
to your use case. You can filter by a standard or custom dimension, such as a campaign, email
domain, or country, or by a custom measurement, such as an email bounce rate over 60%. Available in: Intelligence
There are three different types of filters: Reports and Intelligence
Reports Advanced
• Dimensions — Filters by a dimension. For example, campaign, email domain, or country.
• Custom dimensions — Filters by a customized dimension. For example, filter by an email
name that contains the characters “NTO.” USER PERMISSIONS
• Custom measurements — Filters by a customized measurement. For example, filter by email To apply filters to reports:
bounce rate that is over 60%. • Create & Edit
1. In Analytics Builder, select Intelligence Reports.
2. On the Reports tab, select a report.
3. Under Configuration, click Add Filter.
4. To add a dimension, for example, if you want to filter by the campaign name “Birthday”:
a. Select Custom Dimensions.
b. Search for the required dimension, and enter Campaign.
c. Select the value. In this case, Birthday.
d. To apply the filter, save your work.

126
Marketing Cloud Einstein and Analytics Reports Overview

5. To add a custom dimension, for example, if you want to filter by an email name that contains the characters “NTO”:
a. Select Custom Dimensions.
b. Select the dimension from the dropdown list, and select Email Content Name.
c. Select the operator from the dropdown list, and select Contains.
d. Enter the value in the field. In this case, enter “NTO.”
e. To apply the filter, save your work.

6. You can add multiple operators when filtering to retrieve dimensions that contain specific information according to defined rules.
For example, get all the campaigns that contain the names, ‘“welcome” or “birthday” and that come from audiences that contain
the letters DE.

a. Define the first rule. For example, Audience Name contains DE.
• Select the dimension from the dropdown list, and select Audience Name.
• Select the operator from the dropdown list, and select Contains.
• Enter the value in the field, in this case, enter DE.

b. Define the match either rule. For example, Campaign matches either ‘Welcome’ or ‘Birthday’
• Select the dimension from dropdown list, and select Campaign.
• Select the operator from the dropdown list, and select Matches Either.
• Enter the value in the field. In this case, use an asterisk (*) at the beginning and at the end of the value with a comma
separating the values. For example, *Welcome*, *Birthday*.

c. To apply the filter, save your work.

127
Marketing Cloud Einstein and Analytics Cross-Channel Apps

7. To add a custom measurement, for example, if you want to filter by email bounce rate that equals 80%:
a. Select Custom Measurements.
b. Select the measurement from the dropdown list, and select Email Bounce Rate.
c. Select the operator from the dropdown list, and select Greater Than.
d. Enter the value in the field. In this case, enter 80%.
e. To apply the filter, save your work.

Tip: To add a filter to exclude test emails, search for the Test Email Indicator dimension, and then set it to False. After you do, test
emails don’t appear in your pivot tables or reports.

Cross-Channel Apps
Cross-Channel apps allow you to take your data from separate silos, and then connect, visualize,
EDITIONS
and analyze your key data sources. The apps are available in the Cross-Channel tab, where you can
demo and install various apps. Available in: Intelligence
Note: Every cross-channel app can only be installed once, providing a single account per Reports Advanced
external data provider. With the full Intelligence Reports for Engagement license, you have
access to a vast number of apps, unlimited app installations and you can connect as many
external data providers as needed.

Available Cross-Channel Apps

Intelligence Reports Advanced offers four ready-to-use cross-channel apps.
Manage Cross-Channel App Credentials
Use the app credentials manager to view data sources that you added to your cross-channel apps and the credentials for each data
source. When connecting third-party platforms to your apps, you can add new account credentials, refresh, or update existing
credentials. If a data error occurs with your app, you can access and edit the credentials or log a support ticket.

Available Cross-Channel Apps

Intelligence Reports Advanced offers four ready-to-use cross-channel apps.
EDITIONS
The installation for each app is dynamic and requires unique steps. After you install an app, you can
go to the Dashboards tab, where you can view and access your installed apps in the Cross-Channel Available in: Intelligence
Analysis section. Reports Advanced

Note: All dashboards that are created with cross-channel apps are read-only and can’t be
modified.

Email to Web Conversion GA4 App

The Email to Web Conversion GA4 app combines your Marketing Cloud and Google Analytics data into one view so that you can
easily see how well your email campaigns are performing.
Audience Insights for Advertising Studio App
Connect Marketing Cloud Advertising, formerly known as Advertising Studio to your paid media channels to optimize your audience
strategy with a single, cross-channel view, and analyze the effectiveness of your first-party audiences. Explore how your audiences
are performing across channels with a ready-made dashboard.

128
Marketing Cloud Einstein and Analytics Cross-Channel Apps

Cross-Channel Marketing Insights

The Cross-Channel Marketing Insights app unifies your data to help you make data-driven decisions. Users with a full Intelligence
Reports license can edit and customize the app.
Marketing Insights for Sales Cloud
The Marketing Insights for Sales Cloud solution helps marketing and sales understand how marketing efforts and spend are converting
into revenue. For example, discover weak links in your sales funnel or find business justifications to ramp up or pause a campaign.

Email to Web Conversion GA4 App

The Email to Web Conversion GA4 app combines your Marketing Cloud and Google Analytics data
EDITIONS
into one view so that you can easily see how well your email campaigns are performing.

Note: Starting from July 1st, 2023, this app no longer supports UA360 and is only compatible Available in: Intelligence
with GA4. The new version of this app (Email to Web Conversion GA4) is available and should Reports Advanced
be installed in order to access GA4 data. If you installed the previous version of this app (Email
to Web Conversion Deprecated), you won’t see GA4 data and your UA360 data will not be
updated. It’s recommended you install the new version to access GA4. For more information,
see Install the Email to Web Conversion GA4 App
Installing the app involves these high-level steps:
• Connect Google Analytics data.
• Match campaign names.
• Classify Google Analytics campaign names.
• Classify email campaign names.

Classify Campaign Names

To harmonize your data, the Email to Web Conversion GA4 app relies on matching your Google Analytics and Salesforce Marketing
Cloud campaign names. Therefore, if you use different naming conventions for Google Analytics and Salesforce, you must classify
your campaign names so that the app can locate the data from each source.
Install the Email to Web Conversion GA4 App
Installing the Email to Web Conversion GA4 app requires a Google Analytics account for the web analytics data. You must have UTM
campaigns defined for your emails.
View Email Campaign Performance
Use the Email Campaign Performance dashboard to monitor your campaigns. The dashboard that’s created with this app is read-only
and can’t be modified.
GA4 Fields Available in the Email to Web Conversion App
The Email to Web Conversion GA4 app was rebuilt to work with GA4, and therefore some fields were changed accordingly. This list
displays the old fields that were used in the previous version of the app (Email to Web Conversion Deprecated), and the new fields
that the new app (Email to Web Conversion GA4) uses. These fields appear in the run mode of the app.

Classify Campaign Names

To harmonize your data, the Email to Web Conversion GA4 app relies on matching your Google
EDITIONS
Analytics and Salesforce Marketing Cloud campaign names. Therefore, if you use different naming
conventions for Google Analytics and Salesforce, you must classify your campaign names so that Available in: Intelligence
the app can locate the data from each source. Reports Advanced

129
Marketing Cloud Einstein and Analytics Cross-Channel Apps

Many times a campaign name contains irrelevant information. For example, if your campaign name is Summer_2020_Shoes_Sale and
you want it to say Summer Sale, create a rule that removes the unneeded information and leaves only the name as the final campaign
name.
You have two ways to create a final campaign name:
• Use Contains—Creates a rule that tells the app the final campaign name. For example, if the name contains the letters “ABC,” the
final campaign name is “ABC Campaign.”
• Use a Pattern—Extracts a specific term according to a position and delimiter in the naming convention. You can then use the
extracted term to classify the campaigns. For example, if your naming convention is “summer_sale_1,” you extract the first position,
which is “summer.” You can use the term “summer” as the contains term and classify the campaigns according to the term.

Install the Email to Web Conversion GA4 App

Installing the Email to Web Conversion GA4 app requires a Google Analytics account for the web
EDITIONS
analytics data. You must have UTM campaigns defined for your emails.

Important: If you need to connect to GA4 data you must install the new version of this app: Available in: Intelligence
Email to Web Conversion GA4 app. The previous version of this app (Email to Web Conversion Reports Advanced
Deprecated) doesn’t use GA4 data and the data won’t be updated.

Note: This app supports one conversion rate and one funnel. Multiple funnels aren’t
USER PERMISSIONS
supported. To install Cross-Channel
1. On the Cross-Channel Apps tab, select Email to Web Conversion GA4. apps
• Create & Edit
2. Click Get it Now.
3. Click Get Started.
4. Connect your Google Analytics data.
a. Select your Google Analytics account.
b. Select the websites you want to pull data from.
You can select Google Analytics data, if it exists.

c. Click Next.

5. Match campaign names.

a. From the dimension list, select the dimension that represents your campaign names. Message Send Name is selected by default.
After you select a dimension, a preview of your data appears.
b. Change the date range if needed. For example, if no data appears and you know that you had data in September, change the
date range to September.

6. Classify your Google Analytics campaign names.

Note: If your campaign names already use the final naming convention, click Skip and keep my campaign data as is.

a. To explicitly define the final campaign name, click Use Contains.

• If you’re classifying only a few campaign names, manually enter the information in the Contains and Final Campaign Name
columns, and click Next. For example, in the Contains column, enter ABC, and in the Campaign Name column, enter ABC
Campaign.
• If you must classify many campaign names, click Upload File, and download the CSV template file to ensure that you use
the correct headers and columns. Enter the information in the file, upload it, and then click Next. A preview shows you which
names have been classified.

130
Marketing Cloud Einstein and Analytics Cross-Channel Apps

b. To create final campaign names by matching terms, click Use a Pattern.

• Enter your delimiter, select the position of the campaign name that you’re extracting, and click Apply. For example, if you
want to use the first term in your campaign name, select Position 1. All words in position 1 and the matching delimiter are
highlighted.
• Create an exact match for the position to classify the campaign names.
• If you’re classifying only a few campaign names, manually enter the information in the Contains and Final Campaign Name
columns, and click Next. For example, in the Contains column, enter ABC, and in the Campaign Name column, enter ABC
Campaign.
• If you must classify many campaign names, click Upload File, and download the CSV template file to ensure that you use
the correct headers and columns. Enter the information in the file, upload it, and then click Next.
• After you upload a file, a blue checkmark appears next to the classified names and the progress bar shows how many names
were classified. On the right side, all the extracted campaign names appear with their final campaign names.

c. Save your changes and click Next.

7. Classify your Marketing Cloud campaign names.

a. Click Skip and keep my web analytics data as is to leave the Salesforce Marketing Cloud data as is.
b. To explicitly define the final campaign name, click Use Contains.
• If you’re classifying only a few campaign names, manually enter the information in the Contains and Final Campaign Name
columns, and click Next. For example, in the Contains column, enter ABC, and in the Campaign Name column, enter ABC
Campaign.
• If you must classify many campaign names, click Upload File, and download the CSV template file to ensure that you use
the correct headers and columns. Enter the information in the file, upload it, and then click Next. A preview shows you which
names have been classified.

c. To create final campaign names by matching terms, click Use a Pattern.

• Enter your delimiter, select the position of the campaign name that you’re extracting, and click Apply. For example, if you
want to use the first term in your campaign name, select Position 1. All words in position 1 and the matching delimiter are
highlighted.
• Create an exact match for the position to classify the campaign names.
• If you’re classifying only a few campaign names, manually enter the information in the Contains and Final Campaign Name
columns, and click Next. For example, in the Contains column, enter ABC, and in the Campaign Name column, enter ABC
Campaign.
• If you must classify many campaign names, click Upload File, and download the CSV template file to ensure that you use
the correct headers and columns. Enter the information in the file, upload it, and then click Next.
• After you upload a file, a blue checkmark appears next to the classified names and the progress bar shows how many names
were classified. On the right side, all the extracted campaign names appear with their final campaign names.

d. Click Next.

8. Complete the installation.

a. If you want to change any names, click Review.
b. To install the Email to Web Conversion GA4 app, click Finish.

131
Marketing Cloud Einstein and Analytics Cross-Channel Apps

View Email Campaign Performance

Use the Email Campaign Performance dashboard to monitor your campaigns. The dashboard that’s
EDITIONS
created with this app is read-only and can’t be modified.

Note: If you installed the previous version of this app (Email to Web Conversion Deprecated), Available in: Intelligence
you will only see UA360 data and it will only be updated to the latest processed data. In order Reports Advanced
to connect to your GA4 instance you must install the new version of this app (Email to Web
Conversion GA4). For more information, see Install the Email to Web Conversion GA4 App USER PERMISSIONS
You can filter the dashboard by:
To consume Cross-Channel
• Date—Filter by a specific time period. apps
• Campaign—Filter by a specific campaign. • Access, View & Export,
Schedule, “Create & Edit”
The dashboard contains these sections.

Section Widget Description

Email Web Performance provides an overview of all your email web performance.

Emails Sent The total number of emails sent

during the defined time period

Email Open Rate The total number of emails

opened during the defined
time period

Email Click Rate The total number of emails

clicked during the defined time
period

Daily Visitors The total number of daily

website visitors during the
defined time period

Page Views The total number of pages

viewed on the website during
the defined time period

Visitor Bounce Rate The total visitor bounce rate for

the defined time period

Email + Web Performance A detailed view of all emails

and their performance

Funnel Analysis shows an overview of your website data. You can filter by: Campaign Name and
Email Subject.

Conversion Funnel The number of emails sent and

the percentage opened and
clicked, and the total number
of website visits

Campaign Performance A graph showing campaign

performance based on

132
Marketing Cloud Einstein and Analytics Cross-Channel Apps

Section Widget Description

message open rate versus message sends

Email Detail A detailed view of all your emails

Email Flow Optimization An overview of email flows that you can

filter by a flow type or optimization metric

Email Flows A graph showing your email data based on

the metric you selected (for example, emails
opened)

Email Data Table A detailed view of the total number of

emails opened per campaign

GA4 Fields Available in the Email to Web Conversion App

The Email to Web Conversion GA4 app was rebuilt to work with GA4, and therefore some fields
EDITIONS
were changed accordingly. This list displays the old fields that were used in the previous version of
the app (Email to Web Conversion Deprecated), and the new fields that the new app (Email to Web Available in: Intelligence
Conversion GA4) uses. These fields appear in the run mode of the app. Reports Advanced
If you installed the previous version of this app (Email to Web Conversion Deprecated), you will see
the UA fields, not the GA4 fields.

Note: This list is only relevant to the Email to Web Conversion GA4 app, GA4 is not suggesting an interchangeable solution
between UA data and GA4. For more information about GA4, see GA4 Google Documentation.

UA Fields GA4 Fields

Daily Visitors visitors (total_users)

Page View screenPageViews

Website transactions transactions

Note: The Visitor Bounce Rate has a new calculation to align with GA4. For more information, see GA4 Metrics.

Audience Insights for Advertising Studio App

Connect Marketing Cloud Advertising, formerly known as Advertising Studio to your paid media
EDITIONS
channels to optimize your audience strategy with a single, cross-channel view, and analyze the
effectiveness of your first-party audiences. Explore how your audiences are performing across Available in: Intelligence
channels with a ready-made dashboard. Reports Advanced
Note: Advertising Studio is now Marketing Cloud Advertising. We are still working on updating
the platform so all instances will still be referred to as Advertising Studio until this is done.
Installing the app involves these high-level steps.
• Connect Marketing Cloud Advertising data.
• Connect advertising platform data.

133
Marketing Cloud Einstein and Analytics Cross-Channel Apps

• Classify campaign strategies.

• Review data model mapping.

Install the Audience Insights for Advertising Studio App

Measure how your activated audiences are affecting your leading KPIs, prove the impact of first-party audiences in your campaigns,
and track when and where your first-party audiences are being used.
View Audience Insights for Advertising Studio Data
Use the Audience Insights for Advertising Studio dashboard to optimize campaigns using first-party audiences.

Install the Audience Insights for Advertising Studio App

Measure how your activated audiences are affecting your leading KPIs, prove the impact of first-party
EDITIONS
audiences in your campaigns, and track when and where your first-party audiences are being used.

Note: Advertising Studio is now Marketing Cloud Advertising. We are still working on updating Available in: Intelligence
the platform so all instances will still be referred to as Advertising Studio until this is done. Reports Advanced

Also, you must have Marketing Cloud Advertising Admin permissions to install this app.
1. On the Cross-Channel Apps tab, select Audience Insights for Advertising Studio. USER PERMISSIONS
2. Click Get it Now. To install Cross-Channel
3. Connect your Marketing Cloud Advertising data. apps
• “Create & Edit”
You can use your Marketing Cloud or Marketing Cloud Advertising credentials to connect.
a. If your Marketing Cloud Advertising user is already authenticated, select the username from
the dropdown. Or, if you must authenticate, click Add New Authentication. After you connect, all business units that exist for
your user appear in the dropdown.
b. Select the business unit you want to connect to.
c. Click Next.

4. Connect your advertising platform data.

By default, all Facebook Ads, Twitter Ads, and Google Ads data streams in your workspace are selected automatically. A data stream
is created when you connect data.
a. If you want to remove or add an existing data stream, deselect or select the checkbox next to the data stream.
b. To add a new data stream, click Add New.
c. Click Next.

5. Classify your campaign strategies.

All future campaigns are classified if named according to the naming convention used during the classification process. The app
identifies a few strategies used in Marketing Cloud Advertising, for example, awareness or conversion. You can add or remove
strategies and add classification rules to the strategies created.
a. The left side lists all your campaigns in Marketing Cloud Advertising according to the date range chosen. You can also view
unclassified campaigns.
b. To classify a campaign by a strategy, go to the strategy, and add a contains with the name of your campaign.
The right side lists the strategies. Each strategy has predefined rules that classify your campaigns. You can change the rules to
accommodate your naming conventions.

134
Marketing Cloud Einstein and Analytics Cross-Channel Apps

c. To classify your campaigns according to your own naming conventions, you can upload a classification file by clicking Upload
File.
You can’t see the campaign data for new data streams. However, they’re classified according to the rules you upload.

6. Review your mapping.

Intelligence Reports automatically maps your external audience data from the advertising platforms to the Intelligence Reports data
model. You can edit the mapping if necessary.

7. Complete the installation by clicking Install.

View Audience Insights for Advertising Studio Data

Use the Audience Insights for Advertising Studio dashboard to optimize campaigns using first-party
EDITIONS
audiences.

Note: Advertising Studio is now Marketing Cloud Advertising. We are still working on updating Available in: Intelligence
the platform so all instances will still be referred to as Advertising Studio until this is done. Reports Advanced

Additional Information
• The dashboard that’s created with this app is read-only and can’t be modified. USER PERMISSIONS
• The Google Ads API doesn’t pull excluded audience data.
To consume Cross-Channel
You can filter the dashboard by: apps
• Access, View & Export,
• Platform—Filter by a specific advertising platform.
Schedule, “Create & Edit”
• Date—Filter by a specific time period.
The dashboard contains these sections:

Section Widget Description

Overall View for Campaigns Using First-Party Audiences provides a snapshot of how your campaigns are performing in relation
to impressions, conversions, and spend. This section contains these widgets:

Total Spend The total amount of money spent in all campaigns using
first-party audiences.

Total Impressions The total number of impressions for all campaigns using
first-party audiences.

Total Conversions The total number of conversions for all campaigns using
first-party audiences.

Total # of Audiences The total number of audience lists that are either active
or have errors in Marketing Cloud Advertising. Audiences
in draft don’t appear in the total calculation.

Total # of Audiences Active in The total number of audiences active in campaigns

Campaigns displayed in the current timeframe. These audiences are
either included or excluded from these campaigns.

Audience Usage shows which audiences were used the most and which weren’t used at all in your campaigns.
This section contains these widgets:

135
Marketing Cloud Einstein and Analytics Cross-Channel Apps

Section Widget Description

Top Used Audiences The audiences most used in your campaigns, either as
included or excluded.

Least Used Audiences The audiences least used in your campaigns, either as
included or excluded.

Top Campaigns lists the top-performing campaigns. You can select the relevant audience and then filter by a measurement to
investigate the performance of the top-10 campaigns.
This section contains this widget:

Top 10 Campaigns for Selected Your top-10 campaigns in a bar chart. You can filter by
Audience audiences included or excluded in the campaigns and
organize the campaigns according to different
measurements: impressions, clicks, CPM, media cost,
conversion CPA, and conversion rate.
The Google Ads API doesn’t pull excluded audience data;
therefore no data is found for excluded audiences in
Google Ads.

Which Strategy of Audience Performs Best

Displays which strategies perform best according to the campaign performance. Use the relevant measurements to see how each
strategy performs. You can filter by strategy and audiences used in the different campaigns to see how they react to different strategies.

Detailed Display All - Campaign for Each Audience

Displays all your campaigns and audiences and provides a detailed view.

Cross-Channel Marketing Insights

The Cross-Channel Marketing Insights app unifies your data to help you make data-driven decisions.
EDITIONS
Users with a full Intelligence Reports license can edit and customize the app.

Note: The Cross-Channel Marketing Insights app now supports GA4 and can be selected Available in: Intelligence
alongside UA360 profiles during the installation. In order to pull in GA4 data you must first Reports Advanced
uninstall and then reinstall the app.
With the Cross-Channel Marketing Insights app you can:
• Drill down and compare your campaigns and creatives cross-channel.
• Use Einstein Marketing Insights to get items that you can act on right away.
• Learn about your top and worst performers and their characteristics.
• Start and stop campaigns right from the app.

Install the Cross-Channel Marketing Insights App

When you install the app, your Marketing Cloud data is automatically connected and ready to use. If you don’t need the data, you
can remove it. Installing the Cross-Channel Marketing Insights app requires a Google Analytics account and credentials for each
marketing platform that you want to add.

136
Marketing Cloud Einstein and Analytics Cross-Channel Apps

View Cross-Channel Marketing Insights

Use the Cross-Channel Marketing Insights dashboard to view cross-channel, data-driven insights.

Install the Cross-Channel Marketing Insights App

When you install the app, your Marketing Cloud data is automatically connected and ready to use.
EDITIONS
If you don’t need the data, you can remove it. Installing the Cross-Channel Marketing Insights app
requires a Google Analytics account and credentials for each marketing platform that you want to Available in: Intelligence
add. Reports Advanced
Note: The Cross-Channel Marketing Insights app now supports GA4 and can be selected
alongside UA360 profiles during the installation. If you already installed the app and require USER PERMISSIONS
GA4 profiles, you must first uninstall and then reinstall the app.
To install Cross-Channel
1. On the Cross-Channel Apps tab, select Cross-Channel Marketing Insights.
apps
2. Click Get it now. • “Create & Edit”
3. Connect your marketing channels.
4. Select an existing stream or create one.
5. Add other marketing channels.
6. After your data is connected, click Let’s start.
After the app is finished installing, you can access the app views in the Dashboards tab.

View Cross-Channel Marketing Insights

Use the Cross-Channel Marketing Insights dashboard to view cross-channel, data-driven insights.
EDITIONS
Note: The Cross-Channel Marketing Insights app now supports GA4 and can be selected
alongside UA360 profiles during the installation. In order to pull in GA4 data you must first Available in: Intelligence
uninstall and then reinstall the app. For more information, see Install the Cross-Channel Reports Advanced
Marketing Insights App.
The dashboard contains these tabs: USER PERMISSIONS

Note: The dashboard that’s created with this app is read-only and can’t be modified. To consume Cross-Channel
apps
• Access, View & Export,
Tab Description Schedule, “Create & Edit”

Research Dive into your marketing performance with all

your connected platforms, and view your most
important metrics. Toggle between these views
to expand your analysis:
• Data View—Compare your data metrics
for each platform, such as impressions and
clicks.

• See Totals—View totals for all platforms,

split per metric, within the selected
timeframe.

137
Marketing Cloud Einstein and Analytics Cross-Channel Apps

Tab Description
• Graphic View—Compare how each platform is performing
over time for the selected metric.

Insights Lists the highest and lowest performing campaigns by cost

compared to all cross-channel campaigns. View characteristics that
can help you define changes to improve the metrics.

Einstein Marketing Insights (EMI) Get ways to improve your marketing efforts, such as pausing certain
campaigns or allocating more budget to other campaigns.

Marketing Insights for Sales Cloud

The Marketing Insights for Sales Cloud solution helps marketing and sales understand how marketing efforts and spend are converting
into revenue. For example, discover weak links in your sales funnel or find business justifications to ramp up or pause a campaign.
The Marketing Insights for Sales Cloud solution uses the Leads, Opportunities, Accounts, Contact, Campaigns, and Campaign Members
objects.

Install the Marketing Insights for Sales Cloud Solution

Get insights on the complete sales cycle, from spend to revenue, through return on investment. Using the Marketing Insights for
Sales Cloud solution requires the Cross-Channel Marketing Insights solution with at least one paid ad campaign on a common
advertising platform.
View Marketing Insights for Sales Cloud
Use the Marketing Insights for Sales Cloud dashboard to understand how your marketing efforts and spend are converting into
revenue.

Install the Marketing Insights for Sales Cloud Solution

Get insights on the complete sales cycle, from spend to revenue, through return on investment.
USER PERMISSIONS
Using the Marketing Insights for Sales Cloud solution requires the Cross-Channel Marketing Insights
solution with at least one paid ad campaign on a common advertising platform. To install Cross-Channel
1. On the Cross-Channel Solutions tab, select Marketing Insights for Sales Cloud. solutions
• “Create & Edit”
2. Click Get it now.
A wizard navigates you through the configuration process.

3. Click Start.
4. Connect to your Salesforce CRM data.
• If you’ve already authenticated your CRM data, select the authentication you want to connect to from the dropdown.
• If you haven’t authenticated your CRM data, click Add new authentication and then select the authentication from the
dropdown.

5. Select the time period you want to retrieve CRM data for, and click Apply.
The tables to be extracted from your CRM instance appear on the right. To see the data points, hover over a table with your mouse.

6. Click Next.
7. Preview the fields used to harmonize your CRM data and the CRM objects used, and then click Next.

138
Marketing Cloud Einstein and Analytics Cross-Channel Apps

8. Classify your CRM data.

a. Drag each displayed status to the appropriate data stream type according to how you classify each status, either Lead or Qualified
Lead.
b. When you see the “Statuses successfully classified!” notification, click Next.
c. Drag each displayed stage to the appropriate bucket based on how you classify each stage, either Opportunities or Closed
Won.
d. When you see the “CRM Data successfully connected, harmonized, and classified!” notification, click Next.

9. Connect your ads data.

a. Select the data stream that you want to connect, and click Next.
b. Under Usage, select the fields for each provider.
The harmonization takes place between the Name field in the CRM’s campaign object and the Campaign Name field in Ads,
so they must be identical. If they’re not identical, you must create a pattern or classification.
• Identical—Select if the names of the fields that connect your CRM and campaign data are identical. For example, if the
name is both My Product Summer_Sale in Ads and the CRM.
• Pattern—Select if the name of the fields that connect your CRM and campaign data contain the same naming conventions,
but aren’t identical. Enter the delimiter, select the position, and select which Ads data you want to apply it to. For example,
if the name is Summer_Sale in Ads, and My Product Summer_Sale in the CRM, use a pattern with a space delimiter and
position 3.
• Classification—Select if the field names that you connect your CRM and campaign data to are different. For example, the
campaign is named Summer-campaign in Ads, and My Product Summer_Sale in the CRM. To fix this issue, you can upload
a classification file that categorizes your fields so the platform can recognize the matching fields when they have different
names.

10. After you preview the tables for each data source, click Finish.

View Marketing Insights for Sales Cloud

Use the Marketing Insights for Sales Cloud dashboard to understand how your marketing efforts
USER PERMISSIONS
and spend are converting into revenue.
To consume Cross-Channel
Note: The dashboard that’s created with this app is read-only and can’t be modified.
solutions
The Dashboard contains these tabs: • Access, View & Export,
Schedule, “Create & Edit”

Tab Description
Customer Acquisition Get a high-level overview of your campaign’s performance.
View your sales funnel and how your spend and revenue are
performing in correlation. Also view your conversion rate
between opportunities and closed-wons and the average time
an opportunity takes to convert to a closed-won.

Weak Links Find the weak points within your sales funnel. Get the
conversion rates of the different stages in your funnel and the
average time it takes for a lead to move to the next step.

139
Marketing Cloud Einstein and Analytics Queries

Tab Description
Budget Justification Get the information you must justify budget allocation to your stakeholders. See the
cost of the spend and how it’s converted throughout the cycle to leads, opportunities,
revenue, and return on investment.

Manage Cross-Channel App Credentials

Use the app credentials manager to view data sources that you added to your cross-channel apps
EDITIONS
and the credentials for each data source. When connecting third-party platforms to your apps, you
can add new account credentials, refresh, or update existing credentials. If a data error occurs with Available in: Intelligence
your app, you can access and edit the credentials or log a support ticket. Reports Advanced
In the Apps Credentials Manager table, view data source information such as the creator and the
last time the source was authenticated. You can also edit the user names and passwords for the
USER PERMISSIONS
data sources.
1. In the Cross-Channel tab, click Manage Apps Credentials. To access the app credential
manager
2. Click the data source that you want to edit. • Create & Edit
3. Click Edit.
4. After the platform credential window opens, you can edit the credentials.

Queries
Use Queries to pull granular data and get insights on your subscriber level data. For example, learn
EDITIONS
which subscribers engaged in a particular journey or investigate messages sent to a specific
subscriber. Explore and export results for a deeper understanding of your data. Available in: Intelligence
You can create a query using either the Query Builder or SQL. The Query Builder is a clicks-no-code Reports Advanced
tool. You can create queries automatically based on selected dimensions and measurements. If you
prefer to write queries manually, or need to schedule a large data extract, you can use a SQL editor.

Queries Data View

When querying your data in Intelligence Reports Advanced, there are many fields available. You can view the available data set fields
in the Queries tab, in the Data Set tab in the left pane. Queries unify all the available fields into one Engagement Data table.
Calculated KPI Formulas and Common SQL Functions
You can include calculated KPI formulas in your queries, such as ‘push open rate’ using the SQL tool in Queries.
Query Builder
Use the Query Builder to create queries without code. Select dimensions, measurements, and then and run your query all within
one place. You can also create custom builder calculations inside the Query Builder to create custom fields.
Query Your Data with SQL
You can create queries manually using an SQL editor. You can also use or modify one of the predefined queries in the Query Library.
These represent commonly used queries in Query Builder and SQL formats.
Querying Data Extensions
You can create queries with your engagement data and data extension data all in one place.
Export Your Query Results
Download or export query results to S3, SFTP, Google Cloud Platform, Azure Blob, or email and define an ongoing schedule.

140
Marketing Cloud Einstein and Analytics Queries

Query Export Options

After you create and run your queries, you can download the results locally, export, and schedule an export for your results.
Query Limitations
There are two tools you can use to create queries, the query builder and SQL. SQL should be used for more complex use cases. If
you experience any limitations with the preview or downloading your data, consider the export or schedule export options.
Contact Deletion in Intelligence Reports Advanced
Data protection and privacy compliance is a top priority for Intelligence Reports Advanced. If a contact is deleted through the contact
deletion framework, the subscriber key is deleted in Intelligence Reports within seven days. The events linked to the subscriber aren’t
deleted and are anonymously reflected in reports with no identifiable subscriber information.

Queries Data View

When querying your data in Intelligence Reports Advanced, there are many fields available. You
EDITIONS
can view the available data set fields in the Queries tab, in the Data Set tab in the left pane. Queries
unify all the available fields into one Engagement Data table. Available in: Intelligence
Note: The time zone for the data in the queries module is set to UTC +0, for both SQL and Reports Advanced
Query Builder

Field Name Description Type Example Values

audience_name The name of the audience that Dimension VIP Customers, Birthday Today
the email or message was sent
to.

audience_type The audience type: List or Data Dimension List, Data Extension
Extension.

business_unit The name of the business unit Dimension NTO Rewards

that sent the message.

business_unit_id The ID of the business unit. Dimension 1300648

campaign The Marketing Cloud Campaign Dimension Welcome, Post-Purchase

at the time of the send (if
assigned).

campaign_code The campaign’s code (as given Dimension Welcome, Post-Purchase

by the user).

campaign_end_date The campaign’s end date. Dimension 01 Jan 2021

campaign_id The campaign’s internal ID. Dimension 111

campaign_start_date The campaign’s start date. Dimension 01 Jan 2021

campaign_status The campaign’s status. Dimension InProcess, Deployed

channel The messaging channel type Dimension Email, Mobile Push

contact_entry_mode This mode dictates when the Dimension Single Entry Across All Versions,
contact is eligible to enter a Multiple Entries
journey.

141
Marketing Cloud Einstein and Analytics Queries

Field Name Description Type Example Values

country_code The country code of the user Dimension BR
who engaged with the email.
Note:
• Only available for the U.S.

• Not always available or

accurate due to
dependencies on mail proxy
servers, VPNs, and privacy
controls.

email_domain The email domain for the Dimension gmail.com, salesforce.com

message that was sent, such as
yahoo.com or gmail.com.

email_job_id The unique identifier of the Dimension 97797, 94910

email sent.

email_name The email name at the time of Dimension Shipping Notification, Birthday
send.

email_pre_header The email preheader. A Dimension Welcome, Order today and save!
preheader is the text following
the subject line when an email
is previewed. A preheader is one
of the first three items that a
subscriber sees when viewing
an email.

email_send_type The type of message sent. Dimension Triggered, Standard

Triggered--Anything that uses

event-driven sending queues,
such as SOAP triggered sends
and Transaction Journey and
REST APIs.
Standard--Includes
batched-based sending, for
example, sending by a list or by
a data extension through
Automation Studio or Email
Studio.

email_sender_address The email sender’s address. Dimension welcome@northerntrailoutfitters.net,

postpurchase@northerntrailoutfitters.net

email_sender_name The email sender’s name. Dimension Northern Trail Outfitters, NTO

142
Marketing Cloud Einstein and Analytics Queries

Field Name Description Type Example Values

email_status The email job status at the time Dimension New
of send.

email_subject The email subject at the time of Dimension A 20% off Welcome from NTO,
send. Thanks for your purchase from
NTO!

email_test_indicator A flag that indicates this Dimension true, false

message was part of a test send.

enterprise The name of the enterprise Dimension Northern Trail Outfitters

account (“parent”) that sent the
message.

enterprise_id The ID of the enterprise account Dimension 1079707

(“parent”).

event_date The date and time an event, Dimension 2021-09-22 13:12:36.0

such as an open or click,
occurred.

journey_activity_name The journey activity name. Dimension Welcome - Step 4, Post-Purchase

Step 1

journey_activity_type The journey activity type. Dimension EMAILV2

journey_created_date The date the journey was Dimension 01 Jan 2021

created.

journey_description The journey description. Dimension Cross-Channel Journey

encouraging contacts to review
items and purchase additional
recommended items

journey_id The internal unique identifier of Dimension 792E3165-29F6-4EF0-ABCD-204740FE9EC1

the journey and its version.

journey_last_published_date The last date that the journey Dimension 01 Jan 2021
was published.

journey_modified_date The last date that the journey Dimension 01 Jan 2021
was modified.

journey_name The journey name. Dimension Welcome, Post Purchase

journey_status The journey status: Draft, Dimension Published

Running, Paused, Finishing, or
Stopped.

journey_version The journey version. Dimension 78

mobile_app The app name that the message Dimension 2827E0F5-570A-4B89-A76A-5FCB603C5359

was sent to.

143
Marketing Cloud Einstein and Analytics Queries

Field Name Description Type Example Values

mobile_app_version The version of the app that sent Dimension 4.200713.04
the message.

mobile_device_language The language code of the device Dimension en_US

that the message was sent to.
For example, en_us.

mobile_device_model The hardware model of the Dimension iPhone8

device that the message was
sent to..

mobile_device_os The device operating system Dimension iPhone OS

that the message was sent to.
Either iOS or Android.

mobile_device_os_version The mobile device’s operating Dimension 14.6

system version that the message
was sent to.

mobile_sdk_version The version of the MobilePush Dimension 7.2.1

SDK that sent the message.

push_content_name The name of the content used Dimension Mobile Message June 23,
in the send. 2021(1:43:40 PM)

push_send_name The name of the send definition. Dimension Daily Deal

(For Mobile Studio sends, the
Message Name; for Transactional
API sends, the DefinitionKey; for
Journey Builder sends, the
Activity Name.)

push_send_type The type of message sent: Dimension Interaction

• Triggered-- Anything that

uses event-driven sending
queues, such as SOAP
triggered sends and
Transaction Journey and
REST APIs.

• Standard--Includes
batched-based sending, for
example, sending by a list or
by a data extension through
Automation Studio or
Mobile Studio.

144
Marketing Cloud Einstein and Analytics Queries

Field Name Description Type Example Values

region_code The state of the user who Dimension IL
engaged with the email.
Note:
• Only available for the U.S.

• Not always available or

accurate.

subscriber_id The system-defined unique Dimension 11111111

identifier for a contact.

subscriber_key The unique identifier you define Dimension user1

for a contact.

Calculated KPI Formulas and Common SQL Functions

You can include calculated KPI formulas in your queries, such as ‘push open rate’ using the SQL tool
EDITIONS
in Queries.
This table includes examples of common SQL functions and formulas for calculated KPIs. Available in: Intelligence
Reports Advanced
Output Function Category Example
Email Bounce Rate sum(email_bounces)/sum(email_sends) Calculated 3.02%
as email_bounce_rate Measurement

Email Click Rate sume(m_aliunqiue_cikls/)(ume(m_alisends-)ume(m_alibounces) Calculated 2.66%

as email_click_rate Measurement

Email Click To Open sum(ema_liunqiue_cilks)/sum(ema_liunqiue_opens) Calculated 9.17%

Rate as Measurement
email_click_to_open_rate

Email Deliveries sum(email_sends)-sum(email_bounces) Calculated 74

as email_deliveries Measurement

Email Delivery Rate s(ume(ma_lisends-)ume(ma_libounces/)sume(ma_lisends) Calculated 96.98%

as email_delivery_rate Measurement

Email Open Rate sume(m_aliunqiue_opens/)(ume(m_alisends-)ume(m_alibounces) Calculated 29.00%

as email_open_rate Measurement

Email Unsubscribe Rate sume(m_aliunqiue_unsubsbcires/()ume(m_alisends-)ume(m_alibounces) Calculated 0.54%

as email_bounce_rate Measurement

Event Month date(date_trunc('month', Date 01 Aug 2021

event_date))

Event Quarter date(date_trunc('quarter', Date 01 Jul 2021

event_date))

145
Marketing Cloud Einstein and Analytics Queries

Output Function Category Example

Event Week date(date_trunc('week', Date 02 Aug 2021
event_date))

Event Weekday format_datetime(event_date, Dimension Friday

'EEEE')

Event Year date(date_trunc('year', Date 01 Jan 2021

event_date))

Push Bounce Rate sum(push_bounces)/sum(push_sends) Calculated Measurement 3.02%

as push_bounce_rate

Push Deliveries sum(push_sends)-sum(push_bounces) Calculated Measurement 74

as push_deliveries

Push Delivery Rate (sum(push_sends)-sum(push_bounces)/sum(push_sends) Calculated Measurement 96.98%

as push_delivery_rate

Push Open Rate sum(push_opens)/(sum(push_sends)-sum(push_bounces) Calculated Measurement 29.00%

as push_open_rate

Send Month date(date_trunc('month', Date 01 Aug 2021

send_date))

Send Quarter date(date_trunc('quarter', Date 01 Jul 2021

send_date))

Send Week date(date_trunc('week', Date 02 Aug 2021

send_date))

Send Weekday format_datetime(send_date, Dimension Friday

'EEEE')

Send Year date(date_trunc('year', Date 01 Jan 2021

send_date))

Here is an example of how to use Event Weekday and Email Delivery Rate formulas from the calculated KPI formula table, in order to
retrieve the email delivery rate per subscriber and weekday.
select subscriber_key,format_datetime(event_date, 'EEEE') as event_weekday, sum(email_sends)
as email_sends, sum(email_bounces) as email_bounces,
(sum(email_sends)-sum(email_bounces))/sum(email_sends) as email_delivery_rate
from engagement_data
Where event_date between (now()- INTERVAL '7' DAY) and now()
group by subscriber_key, format_datetime(event_date, 'EEEE')
having sum(email_sends)>0

Here you can see the results of the email delivery rate per subscriber and weekday:

146
Marketing Cloud Einstein and Analytics Queries

Query Builder
Use the Query Builder to create queries without code. Select dimensions, measurements, and then
EDITIONS
and run your query all within one place. You can also create custom builder calculations inside the
Query Builder to create custom fields. Available in: Intelligence
Reports Advanced
Query Your Data with Query Builder
Create queries automatically based on selected dimensions and measurements with
clicks-no-code. You can also use or modify one of the predefined queries in the Query Library. They represent commonly used queries
in Query Builder and SQL formats.
Builder Calculations in the Query Builder
Use a builder calculation to create a custom field, such as click rate and open rate, directly in the Query Builder without using SQL
code.

Query Your Data with Query Builder

Create queries automatically based on selected dimensions and measurements with clicks-no-code.
EDITIONS
You can also use or modify one of the predefined queries in the Query Library. They represent
commonly used queries in Query Builder and SQL formats. Available in: Intelligence
1. On the Queries tab, click Create New Query. Reports Advanced
2. Name your query.
3. Select Builder, and click Create. USER PERMISSIONS
4. Build your query. To use the Query Builder:
• Create & Edit

a. Click the + icons to add the dimensions (1), metrics (2), and filters (3).
b. Run your query (4), and view the query results (5).
c. You can save your query (6) and view it later in the Query Library (7).
d. You can download or export your query results (8) and perform scheduled exports on saved queries.

147
Marketing Cloud Einstein and Analytics Queries

Builder Calculations in the Query Builder

Use a builder calculation to create a custom field, such as click rate and open rate, directly in the
EDITIONS
Query Builder without using SQL code.
A builder calculation differs from a calculated measurement, which is used in a pivot table, report, Available in: Available in:
or dashboard. You can use a builder calculation only when using the Query Builder in the Queries Intelligence Reports
tab. Calculations can be used in a query with attributes from connected data extensions, thus Advanced
enabling you to answer questions, such as what is the click rate per city?

Create a Builder Calculation

Use a builder calculation to create a custom measurement when you have subscriber-level data and you want more information,
such as click rates or open rates. For example, you have geographical location data and you want to see the click rate per city.
Click Rate Builder Calculation Example
Use this example to see how data is pulled from connected data extensions (regions) and engagement data (sends, bounces, and
clicks).

Create a Builder Calculation

Use a builder calculation to create a custom measurement when you have subscriber-level data
EDITIONS
and you want more information, such as click rates or open rates. For example, you have geographical
location data and you want to see the click rate per city. Available in: Intelligence
1. On the Queries tab, click Create New Query. Reports Advanced
2. Name your query.
3. Select Builder, and click Create. USER PERMISSIONS
4. On the left side, click the Data Set tab. To create a builder
calculation:
5. To add a builder calculation, under Builder Calculations, click the plus sign.
• Create & Edit

6. Name the measurement, and add an optional description.

148
Marketing Cloud Einstein and Analytics Queries

7. Enter the logic. Here’s an example of an open rate measurement.

8. Save your work.

9. To use the builder calculation in your query, on the Measurements tab, click the plus sign.
10. From Builder Calculations, select the measurement.
11. Run your query.

SEE ALSO:
Click Rate Builder Calculation Example

149
Marketing Cloud Einstein and Analytics Queries

Click Rate Builder Calculation Example

Use this example to see how data is pulled from connected data extensions (regions) and
EDITIONS
engagement data (sends, bounces, and clicks).
Available in: Intelligence
Region Sends Bounces Clicks Reports Advanced
EMEA 100 5 50

AMER 150 15 65

APAC 90 10 20

Builder Calculations
Logic
Delivered = Sends - Bounces
Formula
[email__sends_[engagement__data]] - [email_bounces_[engagement_data]]

Logic
Click Rate = Clicks/(Sends - Bounces)
Formula
[email_unique_clicks_[engagement_data]] / ([email_sends_[engagement_data]] -
[email_bounces_[engagement__data]])

Query Results
The builder calculations produce these query results.

Region Delivered Click Rate

EMEA 95 0.52

AMER 135 0.48

APAC 80 0.25

Query Your Data with SQL

You can create queries manually using an SQL editor. You can also use or modify one of the
EDITIONS
predefined queries in the Query Library. These represent commonly used queries in Query Builder
and SQL formats. Available in: Intelligence
Note: The syntax used in SQL queries is Presto SQL. Reports Advanced

1. On the Queries tab, click Create New Query.

2. Name your query.
3. Select SQL, and click Create.
4. Write your query.

150
Marketing Cloud Einstein and Analytics Queries

a. Create your query (1) and then run (2) it to view the results.
b. You can save your query (4) and view it later in the Query Library (5).
c. You can download or export your query results (6) and perform scheduled exports on saved queries.

To use SQL Queries most efficiently:

• To wrap a value in quotes, highlight the value and then type “ ‘ “
• To run only a portion of the query in the SQL window, highlight the section and then click Run.
• To copy the value of a cell in the results, right-click the cell and click Copy.

Querying Data Extensions

You can create queries with your engagement data and data extension data all in one place.
EDITIONS
Before you can query data extensions, you first need to connect to data extensions in the Setup
tab. For more information, see Connect to a Data Extension on page 186 Available in: Available in:
Intelligence Reports
After you connect a data extension it appears in its own table in the Library. You can then either
Advanced
use SQL or the Query Builder to query the data.

Create a Query with a Data Extension

Create a query with data extensions to view your engagement data with your data extension data. For example, view total clicks per
region.

Create a Query with a Data Extension

Create a query with data extensions to view your engagement data with your data extension data.
EDITIONS
For example, view total clicks per region.
To query the data extension you can use SQL or the Query Builder. If you’re using SQL, you can Available in: Intelligence
create complex use cases. If you’re using the Query Builder and you want to query both engagement Reports Advanced
data and extension data in the same query, you must make sure you created a join before creating
the query.
USER PERMISSIONS
In this example, you can see how to query engagement data and data extension data using the
Query Builder. To Create a Query:
• Create & Edit
1. On the Queries tab, click Create New Query.
2. Name your query.
3. Select Builder, and click Create.
4. Build your query.

151
Marketing Cloud Einstein and Analytics Queries

For example, create a query to view total clicks per region. In this example, the dimension is Location (taken from the data extension)
and the measurement is email_sends (taken from the engagement data).

5. If you’re using SQL, here’s an example of a join that produces the same results.
select data_extension.Region, sum(data_extension.email_unique_clicks)
from engagement_data left join data_extension on engagement_data.subscriber_id =
data_extension.ID
group by data_extension.Region

6. To run the query, click Run

Export Your Query Results

Download or export query results to S3, SFTP, Google Cloud Platform, Azure Blob, or email and
EDITIONS
define an ongoing schedule.
1. On the Queries tab, create a query or select a saved one. Available in: Intelligence
Reports Advanced
2. Run the query.
3. To download the query results locally, select Download. Only the first 20,000 rows are
downloaded. USER PERMISSIONS
4. To export all the data, click Export To and select the format. To Export Query Results:
5. To export on a scheduled basis, click Scheduled Export. The options change according to the • Create & Edit
format you select. After you set the delivery method and enter your credentials, set the frequency.
For example, set daily to export the results on a daily basis.
6. Save your work.

152
Marketing Cloud Einstein and Analytics Queries

After you save, to view your execution history, go to Options and then select Export History.

SEE ALSO:
Query Export Options

Query Export Options

After you create and run your queries, you can download the results locally, export, and schedule
EDITIONS
an export for your results.

Note: Limitations apply to selected export methods, based on the query tool you’re using Available in: Intelligence
- SQL or Builder. See Query Limitations on page 154 for more information. Reports Advanced

Action Description
Download Download your query locally on your computer.
File format: CSV

Export to Export your query results directly to your

preferred location.
Delivery Methods:
• S3
• SFTP
• Azure Blob
• Google Cloud Storage
• Email (By default, the file format for email is
CSV Friendly Formatting and can’t be
modified)
File Format:
• ORC
• PARQUET
• CSV

Schedule Export Schedule an export to automatically export your

query results based on the frequency you select.
Delivery Methods:
• S3
• SFTP
• Azure Blob
• Google Cloud Storage
• Email (By default, the file format for email is
CSV Friendly Formatting and can’t be
modified)
File Format:
• ORC

153
Marketing Cloud Einstein and Analytics Queries

Action Description
• PARQUET
• CSV
Frequency Options:
• Hourly
• Daily
• Weekly
• Bi-Weekly
• Monthly
• Quarterly
• Yearly

Query Limitations
There are two tools you can use to create queries, the query builder and SQL. SQL should be used
EDITIONS
for more complex use cases. If you experience any limitations with the preview or downloading
your data, consider the export or schedule export options. Available in: Intelligence
This table presents the different actions and their limitations: Reports Advanced

Action Limitation
UI Preview Timeout: 10 Min
Returned Rows: 5,000

Download Returned Rows: 25,000

Export to File Formats: PARQUET, ORC, CSV, and CSV

Friendly Formatting
CSV Friendly Formatting is limited to 2.3M rows
in the results.

Scheduled Export File Formats: PARQUET, ORC, CSV, and CSV

Friendly Formatting
CSV Friendly Formatting is limited to 2.3M rows
in the results.

154
Marketing Cloud Einstein and Analytics Calculated Fields

Contact Deletion in Intelligence Reports Advanced

Data protection and privacy compliance is a top priority for Intelligence Reports Advanced. If a
EDITIONS
contact is deleted through the contact deletion framework, the subscriber key is deleted in
Intelligence Reports within seven days. The events linked to the subscriber aren’t deleted and are Available in: Intelligence
anonymously reflected in reports with no identifiable subscriber information. Reports Advanced

SEE ALSO:
Contact Deletion in Contact Builder

Calculated Fields
Create calculated fields in Intelligence Reports Advanced when you need customized dimensions
EDITIONS
and measurements.
Calculated fields are created in the Setup tab and can then be used in dashboards, pivot tables and Available in: Intelligence
reports. Reports and Intelligence
Reports Advanced

Calculated Dimensions
Calculated Dimensions are non-numerical fields or dimensions that you can create on top of your existing data. Calculated dimensions
don’t exist physically in the database. Rather, each calculated dimension represents a query that can be referenced to from any
report, pivot table, and dashboard page.
Calculated Measurements
Calculated measurements are numerical custom calculations that you can create on top of your existing data. You can create
calculated fields from the widget editor, referencing dimensions and measurements, as well as functions and operators.

Calculated Dimensions
Calculated Dimensions are non-numerical fields or dimensions that you can create on top of your
EDITIONS
existing data. Calculated dimensions don’t exist physically in the database. Rather, each calculated
dimension represents a query that can be referenced to from any report, pivot table, and dashboard Available in: Intelligence
page. Reports Advanced
You can create a calculated dimension from the widgets in the dashboard pages, and there are
many functions you can use. Maintenance is easy and flexible. And any change you make in the
calculated dimension is automatically applied wherever it’s used across your workspace.
You can use calculated dimensions to:
• Consolidate dimensions – If you have dimensions that display long names, such as email addresses, use the IF function to extract
the name of the email without manipulating the actual data that you bring into Intelligence Reports.
For example: IF([Email_Domain] contains 'hotmail.autonto.com', ‘Hotmail’])

• Remove unwanted characters – If a dimension value includes characters that you want to extract, use the Extract() function. Allowing
you to extract the substring, at the given position, after splitting by the given delimiter.
For example, EXTRACT([Email_Name],'-',0) extracts the email name.

155
Marketing Cloud Einstein and Analytics Calculated Fields

Create a Calculated Dimension

Create calculated dimensions on top of existing data so you can refer to them from different tabs. You can also create calculated
dimensions from a widget on a dashboard page. Calculated dimensions created from widgets appear in the calculated dimension
part of the Setup tab.
Calculated Dimension Functions
You can use Functions when creating calculated dimensions.
Calculated Dimensions Use Cases
Use these examples when creating calculated dimensions in Intelligence Reports Advanced to easily create fields. Each example
contains an explanation with a code sample.
Find and Replace Calculated Dimensions
You can use the find and replace function to search for a specific dimension, edit and replace the edited dimension across your
entire business unit. You can do this without searching for the location of the calculated dimension, which is especially useful when
creating a calculated dimension that is meant to replace an existing dimension.

Create a Calculated Dimension

Create calculated dimensions on top of existing data so you can refer to them from different tabs.
EDITIONS
You can also create calculated dimensions from a widget on a dashboard page. Calculated
dimensions created from widgets appear in the calculated dimension part of the Setup tab. Available in: Intelligence
Note: You can create up to 20 additional calculated dimensions at one time per business Reports Advanced
unit. This number does not include the available pre-canned dimensions.
1. From Analytics Builder, select Intelligence [Datorama] Reports. USER PERMISSIONS
2. Select the Setup tab. To Create a Calculated
3. Expand Calculated Dimensions and click Create Calculated Dimensions. Dimension:
• Create & Edit
4. Define your calculated dimension:
In the General section:
• Name your calculated dimension.
• Select the type of calculated dimension you want to create:
– Text — Appears as a string (numbers appear as numbers not text).
– Number — Appears as a number.
– Date — Appears in a date format (according to your settings).
– Link — An active link.
– Image — Appears as a thumbnail.
– Video — Appears as a link to the video in a new browser tab.

Note: The ‘type’ affects the formats available in the dashboard widget settings, in most cases, you should set the type to
Text.

• Add a description of the calculated dimension.

In the Advanced section, you can define advanced settings such as:
• Related Measurement — Select a measurement that is linked to your calculated dimension’s formula, to enable you to populate
lists with calculated dimension values - for example, you have a calculated dimension that returns Email Name with the related
measurement of Clicks. When this calculated dimension is used in a widget, the returned Email Name values will only be of

156
Marketing Cloud Einstein and Analytics Calculated Fields

emails that had at least 1 click within the date range that the page is filtered on. If no related measurement is used, all Email
Names are returned, including those without clicks.
• Invisible Dimension — Select this checkbox to hide any widget that contains this calculated dimension from users who do
not have the ‘Create and Edit’ permission.
In the Expression section, insert the expression you want to base the calculated dimension on. For example, if your customer's
Email Names consist of multiple concatenated values, you can create calculated dimensions to extract these values and create fields
out of them using the formula: EXTRACT([Email_Name],'_',1).
On the right-side menu, use the list of available dimensions and functions to create your expression. Click on a function to add it to
your expression or start typing for auto-complete. You can use any of the available functions together with any of your available
fields.
You can also use any of these options that appear at the bottom of the expression screen:
• Full Screen — Click here to view the Expression section in full-screen mode.
• Auto Format — Click here to format your code into the standard correct structure.
• Comment — Click here to enter a comment within your expression.
• Uncomment — Click here to remove your comment from the expression.
• Code Validation — Click here to validate that your expression is accurate.
• Test — Click here to test your expression.

5. Click Save.

Calculated Dimension Functions

You can use Functions when creating calculated dimensions.
EDITIONS
The functions are divided into these categories:
Available in: Intelligence
• Number Functions
Reports Advanced
• Text Functions
• Date Functions
• Aggregation Functions
• Logical Functions
• Type Conversion
• Content Functions
The following tables summarize the available functions for calculated dimensions.
Number functions

Function Name Syntax Description

ABS ABS(number) Returns the absolute value of a number.

CEILING CEILING(number, significance) Rounds the number up, away from zero, to
the nearest multiple significance.

FLOOR FLOOR(number, significance) Rounds the number down towards zero, to

the nearest multiple significance.

RAND RAND() Gets a random number between 0 and 1.

157
Marketing Cloud Einstein and Analytics Calculated Fields

Function Name Syntax Description

ROUND ROUND(number) Rounds a number to the nearest integer.

ROUND ROUND(number, num_digits) Rounds a number to a specified number of

digits.

Text functions

Function Name Syntax Description

CHAR CHAR(number) Returns a character specified by a number.

COALESCE COALESCE([value1, value2,...]) Returns the first value from the list that isn’t
empty.

CODE CODE(text) Returns a numeric code for the first

character in a text string.

COUNT_CHAR COUNT_CHAR(text, charToCount) Counts how many times a specific character

appears in a text.

EXTRACT EXTRACT(text, delimiter, position) Extracts from the given text the substring,
at the given position, after splitting by the
given delimiter. For example,
EXTRACT(‘a,b,c’,’_’,1) returns ‘b’.

FIND FIND(findText, withinText) Returns the starting position of findText

withinText. Returns -1 if withinText doesn’t
contain findText.

FUZZYMATCH FUZZYMATCH(valueToMatch, array, Searches for a string in an array of values

threshold) that potentially match using
duplicate-detection algorithms that
calculate the similarity of two streams of
data. Returns the matched string from the
array if there’s a match or, if no matches are
found, returns an empty string. For example,
FUZZYMATCH("ABC Company",{"ABC
Company Inc","Apple Inc","IBM
Company"},0.8) returns "ABC Company Inc".
The threshold parameter must be a value
between 0 and 1. A threshold of 1 means
an exact match.

GET_EXCHANGE_RATE GET_EXCHANGE_RATE(date, fromISO, toISO) Get the exchange rate for the given
currencies and date.
The ‘date’ variable in the formula can be a
mapped date field or a date function
For example:

158
Marketing Cloud Einstein and Analytics Calculated Fields

Function Name Syntax Description

• GET_EXCHANGE_RATE([Day], 'USD',
'GBP')

where [Day] is a mapped date field

• GET_EXCHANGE_RATE(DATE('2015','8','17'),'USD','GBP')

where DATE('YYYY','MM','DD') is a date

function.
• GET_EXCHANGE_RATE(YESTERDAY(),'USD','GBP')

where YESTERDAY() is a date function.

INDEXOF INDEXOF(array, findText) Searches the array for the specified item,
and returns its position.
Returns -1 if the item isn’t found.
If the item is present more than once, the
INDEXOF function returns the position of
the first occurrence.
For example, INDEXOF(csv['row'], 'Campaign
ID') == 0 returns true if 'Campaign ID' was
found in the first cell.
Note: The first item has position 0, the
second item has position 1, and so on.

ISEMPTY ISEMPTY(value) Returns if the value is empty or not.

LEFT LEFT(text, numOfChars) Returns the requested number of characters

from the left.

LEN LEN(text) Returns the number of characters in the

given text

LOWER LOWER(text) Converts all upper-case letters in a string to

lower-case letters.

MATCH MATCH(valueToMatch, array) Searches for a specified item in an array of

values, and then returns a boolean result.
For example, MATCH(1,{1,2,3}) returns true
because the value '1' exists in the array.

PROPER PROPER(text) Capitalizes the first letter in a text string and

any other letters in text that follow any
character other than a letter. Converts all
other letters to lowercase letters.

REPLACE REPLACE(SourceStr, pattern, targetStr) Replaces every match of a pattern (a regex

expression) in sourceStr to targetStr. For
example, REPLACE('All-The-Best', '-', ' ')

159
Marketing Cloud Einstein and Analytics Calculated Fields

Function Name Syntax Description

returns 'All The Best'. In another example,
REPLACE('Let It Be','\\s','-') returns 'Let-It-Be'.

RIGHT RIGHT(text, numOfChars) Returns the requested number of characters

from the right.

SELECT SELECT(sourceStr, pattern) Selects the first match of the pattern (a

regex expression) in the sourceStr. For
example, SELECT('Hello B wow E Goodbye',
'B(.*?)E') returns 'B wow E'.

SEMTIMEN SENTIMEN(text) Extracts a positive, neutral, or negative

sentiment from the given text.

SPLIT SPLIT(text, delimiter) Splits a text string into an array by using a

delimiter character. It returns a zero-based,
one-dimensional array holding the parts of
the original text string. For example,
SPLIT('a,b,c', ',') returns an array with three
items.

SUBSTITUTE SUBSTITUTE(text,oldText,newText) Substitutes newText for oldText in a text

string. Use SUBSTITUTE when you want to
replace specific text in a text string.

SUBSTRING SUBSTRING(text,beginIndex,endIndex) Returns the substring of the text beginning

at beginIndex (inclusive) and ending at
endIndex (exclusive).

TRIM TRIM(text) Removes all spaces from the text except for
single spaces between words.

UPPER UPPER(text) Converts all lowercase letters in a text string

to uppercase.

URL_DECODE URL_DECODE(text) Decodes an

application/x-www-form-urlencoded string
using a UTF-8 encoding scheme.

URL_ENCODE URL_ENCODE(text) Translates a text into an

application/x-www-form-urlencoded format
using a UTF-8 encoding scheme.

VALUE_FROM_JSON VALUE_FROM_JSON(JSON string, key) Returns the value for a given key in a JSON
string. If the key doesn’t exist or the JSON is
empty, an empty string is returned.

Date functions

160
Marketing Cloud Einstein and Analytics Calculated Fields

Function Name Syntax Description

DATE DATE(year, month) Returns the first day of the given month in
the given year.

DATE DATE(year, month, day) Returns the date representing the given
arguments.

DATEADD DATEADD(interval, number, date) Returns the date after a specific time or date
interval was added. The interval must be
one of 'yyyy' (year), 'q' (quarter), 'm' (month),
'd' (day), 'ww' (week), 'h' (hour), 'n' (minute),
or 's' (second).

DATEDIFF DATEDIFF(interval,startDate,endDate Returns the number of time units specified

by the interval between the startDate and
the endDate. The startDate and endDate
arguments must be date objects or date
strings in standard form. The interval must
be one of 'yyyy' (year), 'q' (quarter), 'm'
(month), 'd' (day), 'ww' (week), 'h' (hour), 'n'
(minute), or 's' (second).

DAYPRECISION DAYPRECISION(date) Returns the given date with day precision,

meaning the hours, minutes, and seconds
fields are all set to 0. For example, the date
'12-Jun-2012 16:34' is converted to
'12-Jun-2012 00:00'.

DAYSBETWEEN DAYSBETWEEN(startDate, endDate) Returns the number of days between the

given startDate and endDate. The
arguments must be date objects or date
strings in standard form.

DAYSINMONTH DAYSINMONTH(date) Returns the number of days in a specified

month.

NETWORKDAYS NETWORKDAYS(startDate, endDate) Returns the number of workdays between

two dates, excluding weekends. The
arguments must be date objects or date
strings in standard form.

NOW NOW() Returns the current system date and time.

SETHOUR SETHOUR(date, hour) Returns the given date set with the given
hours, with the hours being a numeric value
from 0 through 23.

TODAY TODAY() Returns the current system date.

TOSECONDS TOSECONDS(duration) Returns the number of seconds represented

by the given duration string, with the format
HH:mm:ss/HH:mm:ss.SSS.

YESTERDAY YESTERDAY() Returns yesterday’s system date.

161
Marketing Cloud Einstein and Analytics Calculated Fields

Aggregation functions

Function Name Syntax Description

GROUPCONCAT GROUPCONCAT(groupedDimension, Concatenates the values of
keyDimension, separator) groupedDimension by keyDimension, with
the separator string between each two
grouped values. This process is done
uniquely, that is, the same value repeated
isn’t concatenated twice. For example,
GROUPCONCAT({Media Buy Name},
{Campaign Name}, ',') results in all media
buy names concatenated (with no
repetitions) for each campaign.

Logical functions

Function Name Syntax Description

AND AND(condition1, condition2) Logical AND, checks to see that both
conditions are true.

IF IF(condition,resultifTrue,resultifFalse) Returns the second argument if the first

argument is true, and the third argument if
otherwise.

IFERROR IFERROR(someExpression, number) Returns the someExpression if it’s a valid

number, otherwise returns a number.

NOT NOT(condition) Logical NOT, reverses the logic of its

argument, true becomes false and vice
versa.

OR OR(condition) Logical OR, checks to see if either one of the

conditions is true.

Type conversion functions

Function Name Syntax Description

COMPRESS COMPRESS(value1) Compresses a string using gzip, and returns
it in base64.

DECODE_BASE64 DECODE_BASE64(value1) Decodes a string from base64.

DOUBLE DOUBLE(value1) Converts a string to a double.

ENCODE_BASE64 ENCODE_BASE64(value1) Encodes a string to base64.

FORMATDATE FORMATDATE(date, pattern) Returns the string representation of the

given date according to the supplied
pattern. For example, 'yyyy-MM-dd' -->

162
Marketing Cloud Einstein and Analytics Calculated Fields

Function Name Syntax Description

2014-02-25, 'dd MMM-yyyy' --> 25
Feb-2014, etc.

FORMATDATE_DEFAULT FORMATDATE_DEFAULT(date) Returns the default (yyyy-MM-dd

HH:mm:ss.S) Intelligence Reports string
representation of the given date.

MD5 MD5(stringToHash) Returns an MD5 hash of the given string.

NUMBER NUMBER(value1) Converts a string to a number

PARSEDATE PARSEDATE(dateString, pattern) Returns the date object specified by the

given dateString using the given pattern.
For example, '2014-02-25' --->
'yyyy-MM-dd', '25 Feb-2014' ---> 'dd
MMM-yyyy', etc.

SHA256 SHA256(stringToHash) Returns a SHA256 hash of the given string.

STRIP_HTML STRIP_HTML(value1) Strips HTML from a string.

UNCOMPRESS UNCOMPRESS(value1) Uncompresses a base64 string using gzip.

Context functions

Function Name Syntax Description

CONTEXT_DIMENSION_CONTAINS CONTEXT_DIMENSIONS_CONTAIN(dimension) Returns a 'true' value if the given dimension
is included in the query.

CONTEXT_DIMENSION_EQUALS CONTEXT_DIMENSIONS_EQUALS(dimension) Returns a 'true' value if the given dimensions

are exactly the context dimensions. Enter
all the relevant dimensions, but the order
of appearance isn’t important.

FilterEndDate FilterEndDate() Returns the end date of the query filter.

FilterStartDate FilterStartDate() Returns the start date of the query filter.

GET_ENV GET_ENV(variableName) Returns the value for the given environment

variable. Possible values for variableName
are: WORKSPACE_ID

QUERY_DIMENSIONS_CONTAIN QUERY_DIMENSIONS_CONTAIN(dimension) Returns a 'true' value if the given dimension

is one of the query dimensions.

QUERY_DIMENSIONS_EQUAL QUERY_DIMENSIONS_EQUAL([dimensions]) Returns a 'true' value if the given dimensions

are exactly the query dimensions. Enter all
the relevant dimensions, but the order of
appearance isn’t important.

163
Marketing Cloud Einstein and Analytics Calculated Fields

Calculated Dimensions Use Cases

Use these examples when creating calculated dimensions in Intelligence Reports Advanced to
EDITIONS
easily create fields. Each example contains an explanation with a code sample.

Note: Calculated dimensions can be used in pivot tables, reports, and dashboards, not in Available in: Intelligence
queries. Reports Advanced

Tips:
• For Equals use ‘==’
• For Or use ‘||’
• For And use ‘&&’
• For “not “ use !(expression)
Extract From a Naming Convention
You want to create a dimension based on the naming convention of an existing dimension. For example, the Campaign field is built out
of the following naming convention: countrycode_brandcode_ year_campaign “IL_CK_2022_Welcome”
Formula
EXTRACT(text,delimiter,position)
Description
Extracts the substring from the given text, at the given position, after splitting by the given delimiter. For example, EXTRACT('a_b_c', '_',
1) returns 'b'.
Example
To create a Brand Code field, use this function:
EXTRACT([Campaign],'_',1)

To create a Country field use this function:

EXTRACT([Campaign],'_',0)

Original Data Set

Campaign Email Sends

IL_CK_2022_Welcome 50

IL_CK_2022_Birthday 25

FR_AB_2022_Welcome 70

Results with Calculated Dimension

Country Email Sends

IL 75

FR 70

Extract from a Naming Convention and then Coalesce (between Mobile+Email)

164
Marketing Cloud Einstein and Analytics Calculated Fields

For example, if you store Brand Code in the second position of Push Send Name and in the third position of Email Content Name. In this
case you’re unifying two different fields into one. For example, the Push Send Name field is built with this naming convention: Send
Name_Region (e.g 'Welcome_EMEA). While the Email Content Name field is built with this naming convention: 'BrandCode_Send
Name_Region' (e.g 'A_Birthday_AMER) If you want to create one unified field for the Region from both Email and Push, use the example
formula.
Formula
COALESCE([value1, value2, ...])
Description
Returns the first value from the list that isn’t empty.
Example
To create one field that contains Brand Code for both channels follow this logic.
var Brand_Mobile = EXTRACT([Push_Send_Name],'',1);
var Brand_Email = EXTRACT([Email_Content_Name],'',2);
return COALESCE([Brand_Mobile, Brand_Email]);

Email Data Set

Email Content Name Email Sends

A_Birthday_AMER 10

B_Promotional_EMEA 30

B_Promotional_AMER 15

Mobile Data Set

Push Send Name Push Deliveries

Birthday_AMER 10

Promotional_EMEA 20

Promotional_APAC 15

Results with Calculated Dimension

Region (Calc) Email Sends Push Deliveries

AMER 25 10

EMEA 30 20

APAC 0 15

Group Values of a Dimension

You want to group the values of a field together by category. For example, you want to group all ‘Thank You’ emails and all ‘Welcome’
emails.

165
Marketing Cloud Einstein and Analytics Calculated Fields

Formula
IF(condition,resultIfTrue,resultIfFalse)
Description
Returns the second argument if the first argument is true, and the third argument if otherwise.
UPPER(text)
Description
Converts all lowercase letters in a text string to uppercase.
Examples
To create 2 groups of emails - one for Thank You messages and one for Welcome messages:
IF(UPPER([Email_Subject]) contains 'THANK','Thank-you messages',
IF(UPPER([Email_Subject]) contains 'WELCOME','Introduction messages',[Email_Subject]))

If you have multiple IF/Else cases, you can use this syntax. This is only a suggestion.
if(UPPER([Email_Subject]) contains 'THANK')
{ return 'Thank-you messages'; }
else if(UPPER([Email_Subject]) contains 'WELCOME')
{ return 'WELCOME'; }
else {return [Email_Subject];}

Original Data Set

Email Subject Email Sends

Thanks for your purchase 10

Welcome to Northern Trail Outfitters! 20

A 20% off Welcome from NTO 15

Thanks for signing up 5

Welcome to NTO 10

Thank You for Reaching Out! 15

Results with Calculated Dimension

Grouped Subject (Calculated) Email Sends

Thank-You Messages 30

Welcome Messages 45

166
Marketing Cloud Einstein and Analytics Calculated Fields

Find and Replace Calculated Dimensions

You can use the find and replace function to search for a specific dimension, edit and replace the
EDITIONS
edited dimension across your entire business unit. You can do this without searching for the location
of the calculated dimension, which is especially useful when creating a calculated dimension that Available in: Intelligence
is meant to replace an existing dimension. Reports Advanced
1. From Analytics Builder, select Intelligence [Datorama] Reports.
2. Select the Setup tab. USER PERMISSIONS
3. Expand Calculated Dimensions.
To Find and Replace a
4. Select a calculated dimension from the table. Calculated Dimension:
• Create & Edit
5. Click the Find and Replace icon.

In the Find & Replace window (3), you can see where the selected calculated dimension is used across your business unit. For example,
widgets, reports, or pivot tables.

Toggle on the Replace feature (4). From the dropdown, select the dimension that you want to replace the current calculated
dimension with (5).
You can uncheck any location that you don’t want to replace. For example uncheck a specific widget or report (6).

6. Click Replace.

167
Marketing Cloud Einstein and Analytics Calculated Fields

Calculated Measurements
Calculated measurements are numerical custom calculations that you can create on top of your
EDITIONS
existing data. You can create calculated fields from the widget editor, referencing dimensions and
measurements, as well as functions and operators. Available in: Intelligence
Calculated measurements can be a simple mathematical expression that generates a calculation, Reports Advanced
or they can be a body of code with advanced conditioning and logic. You can use calculated
measurements in dashboards, reports, or pivot tables.
Use Case
You want to calculate the key performance indicators (KPIs) in Intelligence Reports for Engagement, using a different formula. For
example, in Intelligence Reports, the Email Open Rate is calculated by dividing the Unique Email Opens by the Email Deliveries. With
calculated measurements, you can create another version of the Email Open Rate that uses the Email Sends as the denominator instead
of the Email Deliveries. You can also create your own KPIs, in addition to the preconfigured measurements in Intelligence Reports using
Calculated Measurements.

Create a Calculated Measurement

Create calculated measurements on top of existing data so you can refer to them in other tabs. You can also create calculated
measurements from a widget on a dashboard page. Calculated measurements created from widgets appear in the calculated
measurements section in the Setup tab.
Calculated Measurement Functions
Use functions when creating a calculated measurement in Intelligence Reports Advanced to make your functions more dynamic.
Calculated Measurements Use Cases
Use these examples when creating calculated measurements to easily create fields. Each example contains an explanation with a
code sample.
Find and Replace Calculated Measurements
You can use the find and replace function to search for a specific measurement. Then, you can edit and replace the edited measurement
across your entire business unit without finding every location where the calculated measurement is used. This feature is especially
useful when creating a calculated measurement that is meant to replace an existing measurement across your business unit.

Create a Calculated Measurement

Create calculated measurements on top of existing data so you can refer to them in other tabs. You
EDITIONS
can also create calculated measurements from a widget on a dashboard page. Calculated
measurements created from widgets appear in the calculated measurements section in the Setup Available in: Intelligence
tab. Reports Advanced
Note: You can create up to 20 additional calculated measurements at one time per business
unit. This number does not include the available pre-canned calculations. USER PERMISSIONS
1. From Analytics Builder, select Intelligence [Datorama] Reports.
To create, edit, and apply
2. In the Setup tab, expand Calculated Measurements, and click Create Calculated filters
Measurement. • Create & Edit
3. Define your calculated measurement:
In the General section:
• Measurement Name – Enter a name for your measurement.
• Type – Select the metric type, which is a numeric value, percentage, currency, or duration of time.

168
Marketing Cloud Einstein and Analytics Calculated Fields

• Decimal Places – Select the number of decimal places in the measurement. The more decimal places you choose, the more
exact the number is.
• Color – Select the color in which the calculated measurement appears in your collections.
• Description – Enter a description of the calculated measurement.
In the Advanced section:
• Total Aggregation Function – Defines what function is used to calculate the total value of a query. For example, SUM, AVG,
MIN, or MAX. Values that appear in separate rows of a display are all aggregated in the Total row.
• Granularity – Determine the level the calculations for the measurement takes place. You can select a granular level that isn’t
included in the widget. For example, when setting the granularity to Job ID, even if you’re visualizing the measurement at the
Campaign Key level, the calculation still occurs at the job level.
• Treat Nulls As Zeros – To turn null values into zero, select this checkbox. This selection allows nulls to be used in the formulas.
• Include Date in Granularity – When it’s in the query, to include the date in the granularity of the calculation, select this
checkbox.
• Invisible Measurement – To hide widgets containing this measurement from users that aren’t admins, select this checkbox.
In the Expressions section, insert the expression you want to base the calculated measurement on. For example, if you want to
calculate Email Open Rate that uses Email Sends as the denominator instead of Email Deliveries, use this expression:
IFERROR([Email_Unique_Opens]/[Email_Sends], null). The IFERROR function results in the Calculated
Measurement returning null values when the Email Sends equals 0.
• Aggregation Function – The Aggregation Function determines the calculation result for all the produced rows. When a
granularity is set, the underlying calculation produces multiple calculation results, for multiple rows. These rows must be
aggregated into a single row of the displayed dimension. When setting a granularity, you must define how the system performs
this aggregation, for example, SUM, AVG, or MAX. On the right- hand side menu, use the list of available dimensions, functions
and measurements to create your expression. Click on a field to add it to your expression or start typing for auto-complete. You
can use any of the available functions together with any of your available fields.
• Code Validation – Check to see if your code is valid (doesn’t include syntax errors).
• Test – Click to make sure that your code works and the data is extracted correctly.

4. Save your calculated measurement.

Calculated Measurement Functions

Use functions when creating a calculated measurement in Intelligence Reports Advanced to make your functions more dynamic.
The functions are divided into these categories:
• Number
• Text
• Date
• Aggregation
• Logical
• Type Conversion
• Context

Number Functions
Returns a numerical value.

169
Marketing Cloud Einstein and Analytics Calculated Fields

Function Name Syntax Description

ABS ABS(number) Returns the absolute value of a number.

CEILING CEILING(number,significance) Rounds the number up away from zero to

the nearest multiple significance.

EXP_TREND EXP_TREND(metric) Computes an exponential trend line for the

given metric.

FLOOR FLOOR(number,significance) Rounds the number down toward zero to

the nearest multiple significance.

LINEAR_TREND LINEAR_TREND(metric) Computes a linear trend line for the given

metric.

LOG_TREND LOG_TREND(metric) Computes a log trend line for the given

metric.

MOVING_AVG MOVING_AVG(metric, windowSize) Computes a moving average with the given

window size. If windowSize is null or
negative, a fully cumulative average is
computed.

POWER_TREND POWER_TREND(metric) Computes a power trend line for the given

metric.

RAND RAND() Gets a random number between 0 and 1.

ROUND ROUND(number) Rounds a number to the nearest integer.

For example: ROUND(4.2) =4
ROUND(4.6) =5

ROUND ROUND(number,num_digits) Rounds a number to a specified number of

digits.

TREND_SLOPE TREND_SLOPE(metric, windowSize) Computes the linear trend slope in the given
window size. If windowSize is null or
negative, a fully cumulative average is
computed.

Text Functions

Function Name Syntax Description

CHAR CHAR(number) Returns a character specified by a number.

COALESCE COALESCE([value1, value2,...]) Returns the first value from the list that isn’t
empty.

CODE CODE(text) Returns a numeric code for the first

character in a text string.

170
Marketing Cloud Einstein and Analytics Calculated Fields

Function Name Syntax Description

COUNT_CHAR COUNT_CHAR(text,charToCount) Counts how many times a specific character
appears in a text.

EXTRACT EXTRACT(text,delimiter,position) Extracts from the given text the substring

at the given position, after splitting by the
given delimiter. For example,
EXTRACT(‘a,b,c’,’_’,1) returns ‘b’.

FIND FIND(findText,withinText) Returns the starting position of findText

withinText.
For example, FIND('World', 'Hello World')
returns 6.
FIND('aoc', 'Hello World') returns -1.

FUZZYMATCH FUZZYMATCH(valueToMatch, array, Searches for a string in an array of values

threshold) that potentially match using
duplicate-detection algorithms that
calculate the similarity of two streams of
data. Returns the matched string from the
array or an empty string if no matches are
found. For example, FUZZYMATCH("ABC
Compani",{"ABC Company Inc","Apple
Inc","IBM Company"},0.8) returns "ABC
Company Inc". The threshold parameter
must be a value between 0 and 1. A
threshold of 1 means an exact match.

GET_EXCHANGE_RATE GET_EXCHANGE_RATE(date, fromISO, toISO) Gets the exchange rate for the given
currencies and date.
The date variable in the formula can be
either a mapped date field or a date
function.
For example:
GET_EXCHANGE_RATE([Day],
'USD', 'GBP')
where [Day] is a mapped date field.
GET_EXCHANGE_RATE(DATE('2021','8','17'),'USD','GBP')
where DATE('YYYY','MM','DD') is a date
function.
GET_EXCHANGE_RATE(YESTERDAY(),'USD','GBP')
where YESTERDAY() is a date function.

INDEXOF INDEXOF(array, findText) Searches the array for the specified item,
and returns its position.
Returns -1 if the item isn’t found.

171
Marketing Cloud Einstein and Analytics Calculated Fields

Function Name Syntax Description

If the item is present more than one time,
the INDEXOF function returns the position
of the first occurence.
For example, INDEXOF(csv['row'], 'Campaign
ID') == 0 returns true if 'Campaign ID' was
found in the first cell.
Note: The first item has position 0, the
second item has position 1, and so on.

ISEMPTY ISEMPTY(value) Returns if the value is empty or not. For

example, ISEMPTY(‘ab’) returns false.
ISEMPTY(‘’) returns true.

LEFT LEFT(text,numOfChars) Returns the requested number of characters

from the left. For example LEFT(‘abcde’, 2)
returns ‘ab’.

LEN LEN(text) Returns the number of characters in the

given text.
For example LEN(‘abc’) returns 3.

LOWER LOWER(text) Converts all uppercase letters in a string to

lowercase letters. For example,
LOWER(‘AbC’) returns ‘abc’.

MATCH MATCH(valueToMatch,array) Searches for a specified item in an array of

values and then returns a boolean result.
For example, MATCH(1,{1,2,3}) returns true
because the value '1' exists in the array.

PROPER PROPER(text) Capitalizes the first letter in a text string and

any other letters in text that follow any
character other than a letter. Converts all
other letters to lowercase.

REPLACE REPLACE(SourceStr,pattern, targetStr) Replaces every match of a pattern (a regex

expression) in sourceStr to targetStr. For
example, REPLACE('All-The-Best', '-', ' ')
returns 'All The Best'. REPLACE('Let It
Be','\\s','-') returns 'Let-It-Be'.

RIGHT RIGHT(text,numOfChars) Returns the requested number of characters

from the right. For example, RIGHT(‘abcde’,
2) returns ‘de’.

SELECT SELECT(sourceStr,pattern) Selects the first match of the pattern (a

regex expression) in the sourceStr. For

172
Marketing Cloud Einstein and Analytics Calculated Fields

Function Name Syntax Description

example, SELECT('Hello B wow E Goodbye',
'B(.*?)E') returns 'B wow E'.

SEMTIMEN SENTIMEN(text) Extracts a positive, neutral, or negative

sentiment from the given text.

SPLIT SPLIT(text,delimiter) Splits a text string into an array by using a

delimiter character. It returns a zero-based,
one-dimensional array holding the parts of
the original text string. For example,
SPLIT('a,b,c', ',') returns an array with three
items.

SUBSTITUTE SUBSTITUTE(text,oldText,newText) Substitutes newText for oldText in a text

string. Use SUBSTITUTE when you want to
replace specific text in a text string.

SUBSTRING SUBSTRING(text,beginIndex,endIndex) Returns the substring of the text beginning

at beginIndex (inclusive) and ending at
endIndex (exclusive).

TRIM TRIM(text) Removes all spaces from the text except for
single spaces between words. For example,
TRIM('Hello World') returns 'Hello World'.

UPPER UPPER(text) Converts all lowercase letters in a text string

to uppercase. For example, UPPER(‘abC’)
returns ‘ABC’.

URL_DECODE URL_DECODE(text) Decodes an

application/x-www-form-urlencoded string
using a UTF-8 encoding scheme.

URL_ENCODE URL_ENCODE(text) Translates a text into an

application/x-www-form-urlencoded format
using a UTF-8 encoding scheme.

VALUE_FROM_JSON VALUE_FROM_JSON(JSON string, key) Returns the value for a given key in a JSON
string. If the key doesn’t exist or the JSON is
empty, an empty string is returned.

Date Functions

Function Name Syntax Description

DATE DATE(year,month) Returns the first day of the given month in
the given year.

DATE DATE(year,month,day) Returns the date representing the given

arguments.

173
Marketing Cloud Einstein and Analytics Calculated Fields

Function Name Syntax Description

DATEADD DATEADD(interval,number, date) Returns the date after which a certain
time/date interval has been added. The
interval can be one of the following: 'yyyy'
(year), 'q' (quarter), 'm' (month), 'd' (day),
'ww' (week), 'h' (hour), 'n' (minute), or 's'
(second).

DATEDIFF DATEDIFF(interval,startDate,endDate Returns the number of time units specified

by interval between the startDate and the
endDate. The startDate and endDate
arguments can be date objects or date
strings in standard form. The interval can be
one of the following: 'yyyy' (year), 'q'
(quarter), 'm' (month), 'd' (day), 'ww' (week),
'h' (hour), 'n' (minute), 's' (second). For
example, DATEDIFF('m',
PARSEDATE('12/22/2021','MM/d/yyyy'),
PARSEDATE('10/18/2021','MM/d/yyyy'))
returns -2.

DAYPRECISION DAYPRECISION(date) Returns the given date with day precision,so

hours, minutes, and seconds fields are all
set to 0. For example, the date '12-Jun-2012
16:34' is converted to '12-Jun-2012 00:00'.

DAYSBETWEEN DAYSBETWEEN(startDate,endDate) Returns the number of days between the

given startDate and endDate.The arguments
can be date objects or date strings in
standard form.

DAYSINMONTH DAYSINMONTH(date) Returns the number of days in a specified

month.

NETWORKDAYS NETWORKDAYS(startDate,endDate) Returns the number of workdays between

two dates, excluding weekends.The
arguments can be date objects or date
strings in standard form.

NOW NOW() Returns the current system date and time.

SETHOUR SETHOUR(date,hour) Returns the given date set with the given
hours, with hour being a numeric value
between 0 and 23.

TODAY TODAY() Returns the current system date.

TOSECONDS TOSECONDS(duration) Returns the amount of seconds represented

by the given duration string in the format
HH:mm:ss/HH:mm:ss.SSS.

YESTERDAY YESTERDAY() Returns yesterday’s system date.

174
Marketing Cloud Einstein and Analytics Calculated Fields

Aggregation Functions
All aggregation functions look at a data range, as opposed to a single row. You can specify the data range you want the calculated
measurement to consider by defining the set of rows that the function operates on, which is called a window function.
You can define a window function in two ways.
P
• Use GroupByDims within your function, for example SUM([metric],[[groupByDims]])
• Use a syntax that lets you choose in which row the function begins to apply and where it stops, such as SUM(metric, first_index(),
last_index())
If you don’t define the window function, aggregation functions consider all the data included in the query.

Function Name Syntax Description

ACC ACC(metric, [groupByDims], orderByDim, Gives an accumulative sum of the metric
sortOrder) grouped by the dimensions, ordered by the
orderByDim with the given sortOrder (‘ASC’
or ‘DESC’). For example, ACC(‘Clicks’, [‘Media
Buy Key’], ‘Day’, ‘ASC’).

ACC ACC(metric, orderByDim, sortOrder, Gives an accumulative sum of the metric

first_index(), last_index()) ordered by the orderByDim with the given
sortOrder (‘ASC’ or ‘DESC’). The window is
defined as an offset from the current row.
Use first_index()+n and last_index()-n for
the offsets from the first and last row in the
partition. If the last two parameters are
omitted, the entire partition is used.

ACC_SUM ACC_SUM(metric) Computes an accumulating sum for the

given metric. Unlike ACC, this function does
not require you to insert a sort order.

AVG AVG(metric, [groupByDims]) Computes the average of the given metric

grouped by the supplied dimensions.

AVG AVG(metric, first_index(), last_index()) Computes the average of the given metric.
The window is defined as an offset from the
current row. Use first_index()+n and
last_index()-n for offsets from the first and
last row in the partition. If the last two
parameters are omitted, the entire partition
is used.

CORREL CORREL(metric1, metric2, [groupByDims]) Calculates the Pearson Product-Moment

Correlation Coefficient for two sets of values.
Set the appropriate precision when creating
a calculated measurement using correlation.

CORREL CORREL(metric1, metric2, first_index(), Calculates the Pearson Product-Moment

last_index()) Correlation Coefficient for two sets of values.
The window is defined as an offset from the

175
Marketing Cloud Einstein and Analytics Calculated Fields

Function Name Syntax Description

current row. Use first_index()+n and
last_index()-n for the offsets from the first
and last row in the partition. If the last two
parameters are omitted, the entire partition
is used.

COUNT COUNT(metric, [groupByDims]) Counts the number of rows (grouped by

the supplied dimension list) in which the
given metric exists.

COUNT COUNT(metric, first_index(), last_index()) Counts the number of rows (grouped by

the supplied dimension list) in which the
given metric exists.The window is defined
as offsets from the current row. Use
first_index()+n and last_index()-n for offsets
from the first or last row in the partition. If
the last two parameters are omitted, the
entire partition is used (optional).

COUNT COUNTDISTINCT([dimensions], Returns the number of unique appearances

[groupByDims]) of dimension value combinations within the
supplied context dimensions. If no groupBy
dimensions are supplied, the row context
is used.

DENSE_RANK DENSE_RANK([groupByDims], orderField, Computes the dense rank grouped by the

sortOrder) dimensions, ordered by the orderField with
the given sortOrder (‘ASC’ or ‘DESC’). If
groupByDims is omitted, it is calculated over
the entire range.

FIRST FIRST(metric, [groupByDims]) Returns the first value (considering the

results’ date dimension) of the given metric,
grouped by the supplied dimensions.

FIRST FIRST(metric, first_index(), last_index()) Returns the first value (considering the
results’ date dimension). The window is
defined as offsets from the current row. Use
first_index()+n and last_index()-n for offsets
from the first or last row in the partition. If
the last two parameters are omitted, the
entire partition is used..

GROUPCONCAT GROUPCONCAT(groupedDimension,keyDimension, Concats the values of groupedDimension

separator) by keyDimension, with the separator string
between each two grouped values. If a value
is repeated, it’s not concated twice. For
example, GROUPCONCAT({Media Buy
Name}, {Campaign Name}, ',' ) results in all

176
Marketing Cloud Einstein and Analytics Calculated Fields

Function Name Syntax Description

media buy names concated (with no
repetitions) for each campaign.

LAST LAST(metric, [groupByDims]) Returns the latest value (considering the

results’ date dimension) of the given metric,
grouped by the supplied dimensions.

LAST LAST(metric, first_index(), last_index()) Returns the latest value (considering the
results date dimension). The window is
defined as offsets from the current row. Use
first_index()+n and last_index()-n for offsets
from the first or last row in the partition. If
the last two parameters are omitted, the
entire partition is used (optional).

LIFETIME LIFETIME(metric, [groupByDims]) Computes the lifetime aggregation of the

given metric grouped by the supplied
dimensions.

LIFETIME LIFETIME(metric, first_index(), last_index()) Computes the lifetime aggregation of the

given metric. The window is defined as
offsets from the current row. Use
first_index()+n and last_index()-n for offsets
from the first or last row in the partition. If
the last two parameters are omitted, the
entire partition is used (optional).

MAX MAX(metric, [groupByDims]) Computes the maximum of the given metric

grouped by the supplied dimensions.

MAX MAX(metric, first_index(), last_index()) Computes the maximum of the given

metric.The window is defined as offsets from
the current row. Use first_index()+n and
last_index()-n for offsets from the first or last
row in the partition. If the last two
parameters are omitted, the entire partition
is used (optional).

MEDIAN MEDIAN(metric, [groupByDims]) Returns the median (the value lying at the
midpoint of the frequency distribution of all
the values) of a metric across all records. You
can use median only with numeric fields.
Null values are ignored.

MEDIAN MEDIAN(metric, first_index(), last_index()) The window is defined as offsets from the
current row. Use first_index()+n and
last_index()-n for offsets from the first or last
row in the partition. If the last two
parameters are omitted, the entire partition
is used. (optional).

177
Marketing Cloud Einstein and Analytics Calculated Fields

Function Name Syntax Description

MIN MIN(metric, [groupByDims]) Computes the minimum of the given metric
grouped by the supplied dimensions.

MIN MIN(metric, first_index(), last_index()) Computes the minimum of the given metric.
The window is defined as offsets from the
current row. Use first_index()+n and
last_index()-n for offsets from the first or last
row in the partition. If the last two
parameters are omitted, the entire partition
is used (optional).

PERCENTILE PERCENTILE(metric, number, Returns the percentile value of the given

[groupByDims]) metric corresponding to the specified
number. The number must be between 0
and 1 (inclusive), for example, 0.66, and
must be a numeric constant.

PERCENTILE PERCENTILE(metric, number, first_index(), Computes the percentile value of the given
last_index()) metric corresponding to the specified
number. The number must be between 0
and 1 (inclusive), for example, 0.66, and
must be a numeric constant. The window
is defined as offsets from the current row.
Use first_index()+n and last_index()-n for
offsets from the first or last row in the
partition. If the last two parameters are
omitted, the entire partition is used
(optional).

RANK RANK([groupByDims], orderField, sortOrder) Computes the rank grouped by the

dimensions, ordered by the orderField with
the given sortOrder (‘ASC’ or ‘DESC’). If
groupByDims is omitted, it is calculated over
the entire range.

STDEV STDEV(metric, [groupByDims]) Computes the standard deviation of the

given metric grouped by the supplied
dimensions.

STDEV STDEV(metric, first_index(), last_index()) Computes the standard deviation of the

given metric. The window is defined as
offsets from the current row. Use
first_index()+n and last_index()-n for offsets
from the first or last row in the partition. If
the last two parameters are omitted, the
entire partition is used (optional).

SUM SUM(metric, [groupByDims]) Computes the sum of the given metric

grouped by the supplied dimensions.

178
Marketing Cloud Einstein and Analytics Calculated Fields

Function Name Syntax Description

For example, SUM(‘Clicks’, [‘Media Buy Key’,
‘Creative Key’]) returns the sum of clicks per
media buy key and creative key.

SUM SUM(metric, first_index(), last_index()) Computes the sum of the given metric. The
window is defined as offsets from the
current row. Use first_index()+n and
last_index()-n for offsets from the first or last
row in the partition. If the last two
parameters are omitted, the entire partition
is used (optional).

TOTAL TOTAL(metric, [groupByDims]) Computes the total of the metric grouped

by the supplied dimensions, according to
its defined aggregation function.
For example, if a metric m has aggregation
type MAX - TOTAL(‘m’, [Dimensions]) ==
MAX(‘m’, [Dimensions]).

VAR VAR(metric, [groupByDims]) Computes the variance of the given metric

grouped by the supplied dimensions.

VAR VAR(metric, first_index(), last_index()) Computes the variance of the given metric.
The window is defined as offsets from the
current row. Use first_index()+n and
last_index()-n for offsets from the first or last
row in the partition. If the last two
parameters are omitted, the entire partition
is used.

first_index first_index() Returns the number of rows from the

current row to the first row in the partition.

index index() Returns the index of the current row in the

partition.

last_index last_index() Returns the number of rows from the

current row to the last row in the partition.

Logical Functions

Function Name Syntax Description

AND AND(condition1, condition2) Logical AND, checks to see that both
conditions are true.

179
Marketing Cloud Einstein and Analytics Calculated Fields

Function Name Syntax Description

IF IF(condition,resultifTrue,resultifFalse) Returns the second argument if the first
argument is true, and the third argument if
otherwise.

IFERROR IFERROR(someExpression, number) Returns the someExpression if it’s a valid

number. Otherwise, returns a number.

NOT NOT(condition) Logical NOT, reverses the logic of its

argument: true becomes false and vice
versa.

OR OR(condition) Logical OR, checks to see if either one of the

conditions are true.

Type Conversion

Function Name Syntax Description

COMPRESS COMPRESS(value1) Compresses a string using gzip and returns
it in base64.

DECODE_BASE64 DECODE_BASE64(value1) Decodes a string from base64.

DOUBLE DOUBLE(value1) Converts a string to a double.

ENCODE_BASE64 ENCODE_BASE64(value1) Encodes a string to base64.

FORMATDATE FORMATDATE(date,pattern) Returns the string representation of the

given date according to the supplied
pattern. For example, (Fri Dec 22 00:00:00
UTC 2021) returns 22-Dec-2021.

FORMATDATE_DEFAULT FORMATDATE_DEFAULT(date) Returns the default (yyyy-MM-dd

HH:mm:ss.S) Marketing Cloud Intelligence
string representation of the given date. For
example,
DATEADD('d',3,PARSEDATE('12/22/2021','MM/d/yyyy'))
returns (Mon Dec 25 00:00:00 UTC 2021).

MD5 MD5(stringToHash) Returns an MD5 hash of the given string.

NUMBER NUMBER(value1) Converts a string to a number.

PARSEDATE PARSEDATE(dateString,pattern) Returns the date object specified by the

given dateString using the given pattern.
For example,
PARSEDATE('12/22/2021','MM/d/yyyy')
returnsFri Dec 22 00:00:00 UTC 2021.

SHA256 SHA256(stringToHash) Returns a SHA256 hash of the given string.

180
Marketing Cloud Einstein and Analytics Calculated Fields

Function Name Syntax Description

STRIP_HTML STRIP_HTML(value1) Strips HTML from a string.

UNCOMPRESS UNCOMPRESS(value1) Uncompresses a base64 string using gzip.

Context Functions

Function Name Syntax Description

CONTEXT_DIMENSION_CONTAINS CONTEXT_DIMENSIONS_CONTAIN(dimension) Returns true if the given dimension is
included in the query.

CONTEXT_DIMENSION_EQUALS CONTEXT_DIMENSIONS_EQUALS(dimension) Returns true if the given dimensions are

exactly the context dimensions. Enter all
relevant dimensions, but the order isn’t
important.

FilterEndDate FilterEndDate() Returns the end date of the query filter.

FilterStartDate FilterStartDate() Returns the start date of the query filter.

GET_ENV GET_ENV(variableName) Returns the value for the given environment

variable. Possible values are:
WORKSPACE_ID.

QUERY_DIMENSIONS_CONTAIN QUERY_DIMENSIONS_CONTAIN(dimension) Returns true if the given dimension is one

of the query dimensions.

QUERY_DIMENSIONS_EQUAL QUERY_DIMENSIONS_EQUAL([dimensions]) Returns true if the given dimensions are

exactly the query dimensions. Enter all the
relevant dimensions, but the order isn’t
important.

Calculated Measurements Use Cases

Use these examples when creating calculated measurements to easily create fields. Each example
EDITIONS
contains an explanation with a code sample.

Note: Calculated measurements can be used in pivot tables, reports, and dashboards, but Available in: Intelligence
not in queries. Reports Advanced

Tips:
• For Equals use ‘==’
• For Or use ‘||’
• For And use ‘&&’
• For “not” use ‘!’ (expression)
Calculate Your Own Rate

181
Marketing Cloud Einstein and Analytics Calculated Fields

You want to calculate the key performance indicators (KPIs) in Intelligence Reports for Engagement using a different formula. For example,
the Email Open Rate is calculated by dividing the Unique Email Opens by the Email Deliveries. With calculated measurements, create
another version of the Email Open Rate that uses the Email Sends as the denominator instead of the Email Deliveries.
Formula
IFERROR(someExpression, number)
Description
Returns someExpression if it’s a valid number, otherwise it returns a number.
Example
To create Email Open Rate:
IFERROR([Email_Unique_Opens]/[Email_Sends], 0)

Original Data Set

Campaign Email Send Email Unique Opens

Welcome 50 35

Birthday 65 10

Promotion 70 55

Results with Calculated Measurement

Campaign Open Rate (Calculated)

Welcome 70%

Birthday 15%

Promotion 78%

Calculate Filtered Metrics

Create a measurement that’s filtered based on a condition. For example, create a dedicated measurement for clicks from each device
for Mobile clicks, and Web clicks.
Formula
IF(condition,resultIfTrue,resultIfFalse)
Description
Returns the second argument, if the first argument is true, and the third argument if otherwise.
Formula
LOWER(text)
Description
Converts all uppercase letters in a text string to lowercase.

182
Marketing Cloud Einstein and Analytics Calculated Fields

Examples
Desktop clicks metric: IF(Lower([Email_Device_Type])== desktop,[Email_Unique_Clicks],0)

Mobile clicks metric: IF(Lower([Email_Device_Type]) == 'mobile',[Email_Unique_Clicks],0)

Original Data Set

Campaign Email Device Type Email Unique Clicks

Welcome Mobile 40

Welcome Desktop 55

Birthday Desktop 35

Birthday Desktop 70

Birthday Mobile 30

Results with Calculated Measurement

Campaign Mobile Clicks Desktop Clicks

Welcome 40 55

Birthday 30 105

Calculate a Share Metric

You want to calculate the share of unique clicks by any dimension. For example, the share of unique clicks by Email Link Alias.
Formula
SUM(metric, [groupByDims])
Description
Computes the sum of the given metric grouped by the supplied dimensions (optional).
Example
To calculate the share of email unique clicks
[Email_Unique_Clicks]/SUM([Email_Unique_Clicks])

You can then use this metric alongside any relevant dimension, and get the share of the metric according to that dimension.
Original Data Set

Email Link Alias Email Unique Clicks

Header 30

Fill in form 50

Go to site 25

183
Marketing Cloud Einstein and Analytics Calculated Fields

Results with Calculated Measurement

Email Link Alias Share of Clicks (Calculated)

Header 28%

Fill in form 47%

Go to site 23%

Count Distinct Use Case

You want to count the number of unique Email Content Names.
Formula
COUNTDISTINCT([dimensions], [groupByDims])
Description
Returns the number of unique appearances of dimension value combinations, within the supplied context dimensions. If no groupBy
dimensions are supplied, the row context is used by default.
Example
COUNTDISTINCT([Email_Content_Name])+[Email_Sends]-[Email_Sends]

Original Data Set

Campaign Email Content Name

Welcome A_Welcome_AMER

Welcome A_Welcome_EMEA

Birthday A_Birthday_EMEA

Birthday B_Birthday_AMER

Birthday B_Birthday_APAC

Results with Calculated Measurement

Campaign Unique Email Content Names (Calculated)

Welcome 2

Birthday 3

184
Marketing Cloud Einstein and Analytics Calculated Fields

Find and Replace Calculated Measurements

You can use the find and replace function to search for a specific measurement. Then, you can edit
EDITIONS
and replace the edited measurement across your entire business unit without finding every location
where the calculated measurement is used. This feature is especially useful when creating a calculated Available in: Intelligence
measurement that is meant to replace an existing measurement across your business unit. Reports Advanced
1. From Analytics Builder, select Intelligence [Datorama] Reports.
2. Select the Setup tab. USER PERMISSIONS

To Find and Replace a

Calculated Measurement:
• Create & Edit

3. Expand Calculated Measurement (1), and then select a calculated measurement from the table.
4. Click the Find and Replace icon (2).

5. In the Find & Replace window (3), you can see where the selected calculated measurement is used across your business unit. For
example, widgets, reports, or pivot tables.
6. Toggle on the Replace feature (4).
7. From the dropdown, select the measurement that you want to replace the current calculated measurement with (5).
8. You can uncheck any location that you don’t want to replace. For example, uncheck a specific widget or report (6).
9. Click Replace.

185
Marketing Cloud Einstein and Analytics Data Extensions

Data Extensions
Query your engagement data with data extension data to retrieve additional attributes and
EDITIONS
measurements. Identify trends and get marketing insights based on performance by audience
attributes from your data extensions. Available in: Intelligence
For example, if you’re interested in the number of opens and clicks based on the user’s geolocation, Reports Advanced
connect to a data extension that holds your subscriber geolocation data. You can then see where
your users are engaging with your data.

Connect to a Data Extension

Connect to a data extension to pull in additional attributes along with your engagement data. You can connect to any data extension
that’s in your business unit and is below 50 million rows.
Create a Join Between Engagement and Data Extension Data
While connecting to a data extension, you can create a connection between the data extension and engagement data. This way
when querying, you’re pulling in data from both datasets.
Manage Data Extensions
All connected data extensions appear in the Setup tab. From here you can view more information about each data extension. If
errors occur during the sync, they appear here. You can also disconnect a data extension if you no longer require it, and edit joined
fields too.
Troubleshoot Data Extension Failures
During the data extension sync process, different statuses appear. If for some reason the process fails, troubleshoot according to
these guidelines.

Connect to a Data Extension

Connect to a data extension to pull in additional attributes along with your engagement data. You
EDITIONS
can connect to any data extension that’s in your business unit and is below 50 million rows.

Note: Available in: Intelligence

Reports Advanced
• SendLog and synchronized data extensions aren’t supported.
• Make sure your data extension doesn’t contain these columns: date_id, location_id,
dat_account_currency, dat_exchange_rate, pacing_period, pacing_end_date, row_count,
USER PERMISSIONS
or brand_id. To Connect to a Data
• Make sure the data extension doesn’t use the same column name more than once. Extension:
• You can connect to up to 30 data extensions. • Create & Edit

While connecting, create a join between engagement and data extension data to ensure the data
appears correctly. After you connect to a data extension you can then create a query with the data extension’s fields. For more information,
see Queries on page 151
1. From Analytics Builder, select Intelligence [Datorama] Reports.
2. Select the Setup tab.
3. Expand Connected Data Extensions, and then click Connect Data Extension.
All data extensions that exist in your business unit appear in folders, just like they’re set up in Marketing Cloud.

4. Expand the folders until you reach the data extension you’re connecting to.

186
Marketing Cloud Einstein and Analytics Data Extensions

Note: You can only connect to data extensions that haven’t been connected, if the data extension is already connected you
can’t move onto the next step.

5. Click Next.
6. Ensure that all fields are correct, and then click Next.
7. To create a join between your engagement data and data extension data, select the fields you want to connect.

Note: This step is only necessary if you want to query your data extension data together with your engagement data using
the Query Builder. For more information, see Create a Join Between Engagement and Data Extension Data on page 187.

8. Select the Join method you require.

By default, the platform queries data based on the Left Join method. Only matching data from the left table is returned when querying.

9. To return all rows that are found from both tables, even if no match is found, select Full Join.
10. Click Done.
11. After the data extension is connected, you can create a query with the fields from the data extension.

Create a Join Between Engagement and Data Extension Data

While connecting to a data extension, you can create a connection between the data extension
EDITIONS
and engagement data. This way when querying, you’re pulling in data from both datasets.
This step is optional and is only necessary if you want to query your data extension data with your Available in: Intelligence
engagement data using the Query Builder. If you want to query your data extension as a standalone Reports Advanced
table without engagement data, then don’t create a join.
There are two different types of joins
• Left Join—Returns all records from the left table, and the matched records from the right table. This is the default type.
• Full Join—Returns all records when there’s a match in either the left or right table.
Use this example, which demonstrates subscriber data, to understand what happens when selecting each join type. You can perform
the join on any field.
Engagement Data

Subscriber Key Sends

abc123 1

187
Marketing Cloud Einstein and Analytics Data Extensions

Subscriber Key Sends

def123 1

aaa222 1

Data Extension Data

ID Region
abc123 EMEA

def123 AMER

123456 AMER

aaa222 EMEA

Since the values are stored in different fields in the data extension and in the engagement data, you must ensure that the fields are
connected. If subscriber data is represented as the subscriber key in your engagement data, and as contact ID in the data extension data,
connect the fields like this:

By default, the system performs a left join. If you run the query, you get these results based on the type of join you select.
Left Join Results

ID Region Sends
abc123 EMEA 1

def123 AMER 1

aaa222 EMEA 1

Full Join Results

ID Region Sends
abc123 EMEA 1

def123 AMER 1

aaa222 EMEA 1

123456 AMER NULL

188
Marketing Cloud Einstein and Analytics Differences Between Intelligence Reports and Other Reports

Manage Data Extensions

All connected data extensions appear in the Setup tab. From here you can view more information
EDITIONS
about each data extension. If errors occur during the sync, they appear here. You can also disconnect
a data extension if you no longer require it, and edit joined fields too. Available in: Intelligence
1. From Analytics Builder, select Intelligence [Datorama] Reports. Reports Advanced
2. Select the Setup tab and then expand Connected Data Extensions.
3. View the different statuses. If a data extension fails, explore why. For more information, see USER PERMISSIONS
Troubleshoot Data Extension Failures on page 189.
To Manage Data Extensions:
4. To disconnect a connected data extension, click Delete. • Create & Edit

Note: After you disconnect a data extension, you can’t query any of the related fields in
the Query tab.

5. To edit the connected fields, click Edit. For more information, see Create a Join Between Engagement and Data Extension Data on
page 187.

Troubleshoot Data Extension Failures

During the data extension sync process, different statuses appear. If for some reason the process
EDITIONS
fails, troubleshoot according to these guidelines.

Note: It’s recommended to not modify data extensions after they’re connected to avoid Available in: Intelligence
sync failures. Reports Advanced

• Pending—The data extension is connecting. It can take up to 24 hours to populate data.

• Complete—The data extension is connected. Data is synced once a day.
• Failed—The data extension failed to sync. Here are some possible reasons:
– A field was renamed or deleted from the data extension. It’s recommended you disconnect the data extension and then contact
Marketing Cloud support.
– There were invalid column names in your data extension.
– The data extension contained one of these column names: date_id, location_id, dat_account_currency, dat_exchange_rate,
pacing_period, pacing_end_date, or row_count.
– The data extension contained the same column name more than once.

Note: Data extensions aren’t case sensitive. For example: campaign name = campaign_name

– A technical error occurred. It’s recommended to wait 24 hours. If this doesn’t help, contact Marketing Cloud support.
– If for some reason the connection to the data extension failed, try deleting the automation of the data extension in Automation
Studio. If this doesn’t help, contact Marketing Cloud support.

Differences Between Intelligence Reports and Other Reports

When using other Marketing Cloud reporting tools, such as Data Views, the results you see can vary
EDITIONS
depending on the type of report and its purpose.
If the results you’re seeing don’t match, the logic behind the reports and structure is different. This Available in: Intelligence
section compares Intelligence Reports to other Marketing Cloud reports so you can understand Reports and Intelligence
and analyze your results accurately. Reports Advanced.

189
Marketing Cloud Einstein and Analytics Set Up Intelligence Reports on Hyperforce - India Only

Intelligence Reports Versus Data Views

When using Intelligence Reports and Data Views, you might encounter discrepancies because the logic behind the reports and
structure is different. Review the differences so that you can better understand your results.

Intelligence Reports Versus Data Views

When using Intelligence Reports and Data Views, you might encounter discrepancies because the
EDITIONS
logic behind the reports and structure is different. Review the differences so that you can better
understand your results. Available in: Intelligence
Reports and Intelligence
Table 5: Intelligence Reports Versus Data Views
Reports Advanced.
Intelligence Reports Data Views
Date range The last date is included in The last date of the date range
Intelligence Reports might not be included,
dashboards. For example, for depending on the query. For
the date range January example, EventDate < 1/31
1–January 31, January 31 is compared to EventDate <=
included. 1/31.

Filtering Test Sends are filtered out of Deleted contacts are filtered
Email OOB dashboards. out of Data Views.
Suppress from Send Reports are
filtered out of all dashboards,
pivot tables, and reports.

Time zone The parent business unit’s time The system time zone (Central
zone is used. Standard Timezone) is used.

Historical data Kept up to 2 years. Only the past 6 months is kept.

Set Up Intelligence Reports on Hyperforce - India Only

Configure your Data Cloud connection to support Hyperforce. Using Hyperforce requires a new connection between Data Cloud and
Marketing Cloud. Intelligence Reports provisioned for Marketing Cloud Engagement is hosted on a Salesforce-managed Hyperforce
infrastructure in the AWS India region. Intelligence Reports on Hyperforce uses data service credits on Data Cloud.

Note: Intelligence Reports on Hyperforce is currently only available for the India region.

To set up Intelligence Reports on Hyperforce you must do the following:

• Open a ticket with Salesforce support and request Intelligence Reports on Hyperforce provisioning.

Important: You must wait for the support ticket to be resolved before connecting Data Cloud to Marketing Cloud.

• After Salesforce support has confirmed your Hyperforce provisioning, in Data Cloud, set up a Marketing Cloud Connection.
If you already have a connection to Marketing Cloud, delete it, and create a new connection.

• Within 48 hours after creating the connection, install the Email and MobilePush data bundles for the new connection.
When connecting the bundles, select all the business units.

190
Marketing Cloud Einstein and Analytics Google Analytics Integration for Marketing Cloud

• Access Intelligence Reports by logging in to Marketing Cloud Engagement with an Intelligence Reports for Engagement user role
on page 67.

Billing for Intelligence Reports on Hyperforce

When you use Intelligence Reports on Hyperforce, your engagement data is stored and processed in Data Cloud. Using Data Cloud
features for Intelligence Reports has billing implications.

SEE ALSO:
Access Intelligence Reports

Billing for Intelligence Reports on Hyperforce

When you use Intelligence Reports on Hyperforce, your engagement data is stored and processed in Data Cloud. Using Data Cloud
features for Intelligence Reports has billing implications.
Data Cloud services and usage impacts the consumption of credits used for billing. Enabling Intelligence Reports creates data streams
to import data from all Marketing Cloud Engagement business units into Data Cloud, even if only a subset of business units are selected
for Data Cloud integration. For more information about usage types, see Data Cloud Usage Types.

Type Description
Batch Data Pipeline Usage is calculated based on the amount of batch data ingested
into Data Cloud data streams. Intelligence Reports creates data
streams for batch processing of engagement data.

Data Queries Usage is calculated based on the number of records processed.

Intelligence Reports periodically executes queries to aggregate
data for generating pivot tables and reports.

Streaming Data Pipeline Usage is calculated based on the number of records ingested by
data streams with stream processing and the number of records
included in data transforms. Intelligence Reports creates data
streams to process engagement records with stream processing.

Data Storage Usage is calculated based on the amount of storage used above
the amount allocated. Intelligence Reports retains engagement
event data in Data Cloud for up to 2 years.

For more information on how Data Cloud usage is billed, refer to your contract or contact your account executive.

Google Analytics Integration for Marketing Cloud

This integration lets you track and analyze journey activity through your Google Analytics account without assistance from technical
support or services. You determine the URL tags and how data is collected and presented in the customizable Google Analytics reporting
dashboard. Use Google’s native authentication to securely link your Marketing Cloud and Google Analytics 360 or Google Analytics Free
accounts.

Important: A change to the Google Analytics Data API (GA4) on January 12, 2023 impacts campaign data in Journey Builder.
Campaign data before November 1, 2022 isn’t accessible through Salesforce Marketing Cloud’s GA4 reporting integration. The

191
Marketing Cloud Einstein and Analytics Google Analytics Integration for Marketing Cloud

change impacts only GA4 properties and doesn’t change any Universal Analytics properties. To view the affected data, create
reports in Google Analytics using these dimensions:

Marketing Cloud Dimension GA4 Traffic Source Dimension

Messaging Channel (email, SMS, push notification) medium

JourneyID campaign ID

Journey Name campaign name

Journey Activity Name source

Note: This feature requires Journey Builder and Google Analytics integration, and requires that you have at least a Marketing
Cloud Enterprise 2.0 account type and a Google Analytics UA Standard Account. Contact your account representative for more
information. The integration connects at the enterprise level. You can revoke the integration from a Google Analytics account.
Google Analytics Free users get access to sampled data reporting about their customer interactions. Marketing Cloud adheres to Google’s
sampling rate. Go to Google Analytics Help for more information about data sampling and sampling rates.
Google Analytics 360 users get access to unsampled data and audiences, empowering them to act on the reporting that Google and
Salesforce provide. Google Analytics 360 customers can market to customers in your audiences in Journey Builder using the Google
Analytics 360 entry source.
For this integration, Google recommends that customers designate a primary company account to track all properties and views by
following the steps demonstrated in this video. For more information, see the Google Hierarchy of organizations, accounts, users,
properties, and views.
Before you configure Google Analytics Integration for Marketing Cloud:
• Confirm that you have administrator permissions for Marketing Cloud and the Google Analytics account and property. To give other
users access, see the Configure Google Analytics Integration Permission page.
• Create a Google Analytics tracking code and add the code to your website’s pages.
• To receive conversion data, enable ecommerce in your Google Analytics 360 account. Ecommerce is available in Google Analytics
360 accounts only.

Configure the Google Analytics Integration for Marketing Cloud

A user with admin rights can follow these steps to set up the integration between Marketing Cloud and your Google Analytics 360
or Google Analytics Free account.
Google Analytics Audience Activation
Audience activation creates a persistent user ID for each shared Marketing Cloud and Google Analytics subscriber. Use the behavioral
data that you collect to create Google Analytics audiences you can use in Journey Builder.
Google Analytics Metrics
Learn about the metrics and dashboard tiles available on the Journey Analytics dashboard with the Google Analytics 4 integration.
The dashboard enables you to view journey performance against the goals you set and email and site metrics all in one place. App
and web conversion events appear in context with your journey’s native metrics. To display the metrics that matter most to you,
customize your dashboard’s appearance.
Google Analytics Integration FAQs
Review answers to frequently asked questions about the Google Analytics Integration with Marketing Cloud.

192
Marketing Cloud Einstein and Analytics Configure the Google Analytics Integration for Marketing
Cloud

Google Analytics Tracking

To get both web and mobile app metrics in the Journey Analytics dashboard, set up Google Analytics tracking for app and web. You
can then analyze how mobile app conversions impact web behavior.

SEE ALSO:
Google Hierarchy of organizations, accounts, users, properties, and views
Google Hierarchy of organizations, accounts, users, properties, and views
About data sampling
Configure Google Analytics Integration User Permission
Journey Analytics Dashboard

Configure the Google Analytics Integration for Marketing Cloud

A user with admin rights can follow these steps to set up the integration between Marketing Cloud and your Google Analytics 360 or
Google Analytics Free account.

Important: Journey Builder and the Google Analytics 360 Integration must be enabled on your account to use the Google
Analytics 360 integration. Contact your account executive for more information.
For information about Marketing Cloud tools available to manage data protection and privacy, see the related links section of this page.
For details about Google’s data protection and privacy tools, refer to Google’s General Data Protection Regulation. To begin setup of the
integration, click Complete to confirm that these prerequisites are completed.

1. Link Google Analytics and Marketing Cloud Accounts

Follow these steps to configure the Google Analytics 360 or Google Analytics Free integration with Marketing Cloud. Google’s native
authentication process creates a secure connection between your Marketing Cloud and Google Analytics accounts and sets view
permissions for your reports.
2. Select Google Analytics Views
Ensure that your Journey Builder dashboards are populated with data. Set up properties and views in your Google Analytics Free or
Google Analytics 360 account. Select the Google Analytics properties and views to access for each business unit in your Marketing
Cloud account.
3. UTM Parameters
The Google Analytics integration with Marketing Cloud tracks certain UTM parameters. The UTM parameters, which are appended
to the URL, identify the marketing campaign that refers traffic to your website.
4. Configure Google Analytics Integration User Permission
Configure permission to access Google Analytics integration features to users that you select. This task requires administrator role
permissions.

SEE ALSO:
Consent Management for Marketing Cloud
Data Deletion for Marketing Cloud
Data Access and Export for Marketing Cloud
Restrict Data Processing for Marketing Cloud

193
Marketing Cloud Einstein and Analytics Configure the Google Analytics Integration for Marketing
Cloud

Link Google Analytics and Marketing Cloud Accounts

Follow these steps to configure the Google Analytics 360 or Google Analytics Free integration with Marketing Cloud. Google’s native
authentication process creates a secure connection between your Marketing Cloud and Google Analytics accounts and sets view
permissions for your reports.

Important: This feature requires Journey Builder and Google Analytics 360 or Google Analytics Free integration. Contact your
Marketing Cloud account representative for more information.

Tip: We recommend that you create a dedicated user account with admin rights to link Marketing Cloud and Google Analytics.

1. In Setup, click Apps, then click Google Analytics Integration.

2. Expand the Data Access Setting section, and click Link Account.

Note: Linking works at the EID level.

3. Select or enter the name of the Google Analytics account, and click Next.
4. Enter your password, and click Next.
A window shows the information that Marketing Cloud accesses.

5. To accept Google’s request to access Marketing Cloud, click Allow.

Tip: To disconnect the account, click Unlink Account.

Select Google Analytics Views

Ensure that your Journey Builder dashboards are populated with data. Set up properties and views in your Google Analytics Free or
Google Analytics 360 account. Select the Google Analytics properties and views to access for each business unit in your Marketing Cloud
account.
Before selecting views, connect your Google Analytics and Marketing Cloud accounts.

Tip: To review how Google defines accounts, properties, and views, see Google’s Hierarchy of organizations, accounts, users,
properties, and views page.
1. In Setup, navigate to Apps, and select Google Analytics Integration.
2. Expand the Integration section, and click Select Views.
3. Locate and add the properties and views that you want to populate your Journey Builder dashboards with.
Properties and views turn into checkmarks when selected.
4. Save your changes.
5. Click Update.

Edit Google Analytics Views for a Business Unit

Change the Google Analytics 360 or Google Analytics Standard properties and views for a business unit accessed by Marketing Cloud
Journey Builder.

Edit Google Analytics Views for a Business Unit

Change the Google Analytics 360 or Google Analytics Standard properties and views for a business unit accessed by Marketing Cloud
Journey Builder.

194
Marketing Cloud Einstein and Analytics Configure the Google Analytics Integration for Marketing
Cloud

1. In Setup, navigate to Apps and click Google Analytics Integration.

2. Expand the Data Access Setting section, and click Edit Access.
3. To add or remove a view, select or deselect it.

UTM Parameters
The Google Analytics integration with Marketing Cloud tracks certain UTM parameters. The UTM parameters, which are appended to
the URL, identify the marketing campaign that refers traffic to your website.

Important: Only the Campaign Source, Campaign Medium, Campaign Name, sfmc_activityID, and Campaign ID parameters are
tracked for SMS activities. Campaign Term, Campaign Content, and Subscriber ID aren’t tracked. For Google Analytics Free users,
the Subscriber ID (sfmc_id) and Campaign Source (utm_source) fields aren’t tracked.

Example: This example string includes populated UTM parameters, which appear in bold text.
https://www.nto.com?utm_source=sfmc&utm_medium=email&utm_campaign=TestCampaign&utm_term=MyLink123&utm_content=123456&utm_id=
f521708e-db6e-478b-9731-8243a692c2d5&sfmc_id=245678&sfmc_activityid=598741568

Campaign Source (utm_source) Use this configurable parameter to track the source of web activity.

Campaign Medium (utm_medium) This configurable parameter tracks which channels, such as email
or SMS, drive the web activity.

Campaign Name (utm_campaign) Use this configurable parameter to identify a product promotion
or strategic campaign. There are two options.
• Set per Message—You can enter a custom campaign name
for each email activity in the Journey Builder Email Send Flow.
• Message Name—The campaign name inherits the name of
the email sent.

Campaign Term (utm_term) This required, nonconfigurable parameter analyzes individual links
within messages. This parameter is populated with link alias text
associated with the content asset.

Campaign Content (utm_content) This required, nonconfigurable parameter tracks the effectiveness
of a Marketing Cloud content asset. This parameter is populated
with the content asset ID associated with the content asset.

Campaign ID (utm_id) This required, nonconfigurable parameter links activity within a

Marketing Cloud journey and is populated with the journey ID.
Marketing Cloud generates this parameter to link activity in Journey
Builder.

Subscriber ID (sfmc_id) This required, nonconfigurable parameter is required when creating

persistent user IDs for the Audience Activation feature.

Activity ID (sfmc_activityid) This required, nonconfigurable parameter is appended to every

link in a journey for supported channels. When a link is clicked, this
parameter is passed to and consumed by Google Analytics from
the URL. The associated Google Analytics behavioral metrics are
then reported for the specific activity in a journey.

195
Marketing Cloud Einstein and Analytics Google Analytics Audience Activation

For more information about the tracked UTM parameters, see Google Custom Campaign Parameters.

SEE ALSO:
Google Custom Campaign Parameters

Configure Google Analytics Integration User Permission

Configure permission to access Google Analytics integration features to users that you select. This task requires administrator role
permissions.

Important: Log out of Marketing Cloud before you begin this task.

1. Complete the steps to Assign a Role and Permissions to a Marketing Cloud User from the Users Screen.
2. In Marketing Cloud Setup, click Apps, then click Google Analytics Integration.
3. To allow view only permissions to desired accounts, select view only for the user’s properties and views.

Tip: Allow edit permissions for administration, tracking, and audiences to the account administrators.

4. Save your changes.

Google Analytics Audience Activation

Audience activation creates a persistent user ID for each shared Marketing Cloud and Google Analytics subscriber. Use the behavioral
data that you collect to create Google Analytics audiences you can use in Journey Builder.

Note: This feature is available to customers with the Google Analytics Integration enabled to their Enterprise 2.0 account. Contact
your account executive for information.
The Marketing Cloud Subscriber ID UTM parameter (sfmc_id) is added to the Google UTM parameters that are appended to links in
Marketing Cloud messages. When a subscriber clicks a link in a message, this action links the Subscriber ID to the Google Client ID. Google
uses the parameter to identify shared contacts.
Google captures the subscriber’s subsequent online activity, including actions such as abandoned cart, goal non-completes, page exits,
abandoned browser sessions, and abandoned searches. You can use this data to create up to 2,000 audiences to import into Journey
Builder with the Google Analytics Audience Entry Activity. In Journey Builder, you can apply filters based on dimensions and metrics for
each subscriber.

Note: Subscriber IDs do not match retroactively, so the match rate is 0% until the audience syncs. Audiences sync every 24 hours,
or according to the schedule you set.

Create a Google Analytics Audience

Create an audience in Google Analytics, and add Marketing Cloud as a destination to use the audience as an entry source in Journey
Builder. When published, the audience syncs every 24 hours, or according to the schedule you set.

196
Marketing Cloud Einstein and Analytics Google Analytics Metrics

Schedule Google Analytics Audience Updates

Configure your Google Analytics audiences so that they update according to the schedule you set. You can choose to set an hourly,
daily, weekly, or monthly schedule.

SEE ALSO:
Configure Default Google Analytics Tracking Parameters
The Google Analytics 360 Entry Source
GA360 Use Case
Contact Builder Data Sources
Synchronized Data Sources in Contact Builder

Create a Google Analytics Audience

Create an audience in Google Analytics, and add Marketing Cloud as a destination to use the audience as an entry source in Journey
Builder. When published, the audience syncs every 24 hours, or according to the schedule you set.
Follow the steps at Salesforce Marketing Cloud audience integration to link to your Marketing Cloud account from your Google Analytics
property.
To create an audience, follow Google’s steps at Create and edit audience.

Important: If you disable Google Analytics tracking for a journey, the resulting audience could be smaller than expected.

SEE ALSO:
Configure Default Google Analytics Tracking Parameters
The Google Analytics 360 Entry Source
Contact Builder Data Sources
Synchronized Data Sources in Contact Builder

Schedule Google Analytics Audience Updates

Configure your Google Analytics audiences so that they update according to the schedule you set. You can choose to set an hourly,
daily, weekly, or monthly schedule.
1. In Contact Builder, navigate to Data Sources.
2. In the Refresh Schedule column, click Edit.
a. When you set a daily schedule, choose the hour that the sync happens.
b. When you set a weekly schedule, choose the day and hour that the sync happens.
c. When you set a monthly schedule, choose the day of the month that the sync happens.

Google Analytics Metrics

Learn about the metrics and dashboard tiles available on the Journey Analytics dashboard with the Google Analytics 4 integration. The
dashboard enables you to view journey performance against the goals you set and email and site metrics all in one place. App and web
conversion events appear in context with your journey’s native metrics. To display the metrics that matter most to you, customize your
dashboard’s appearance.

197
Marketing Cloud Einstein and Analytics Google Analytics Metrics

To learn how to enable Google Analytics 4 tracking for a journey, visit Enable Google Analytics 4.

Journey Analytics Dashboard

Access unified cross-channel performance data in Journey Builder, and easily track your marketing campaign’s effectiveness. Journey
Analytics, powered by Google Analytics, unites Marketing Cloud SMS, push messaging, and email capabilities with Analytics behavioral
data in a single dashboard. You can compare how goals configured in Google Analytics perform over time, and you can see ecommerce,
messaging performance, and site usage data.
Use the Journey Analytics Dashboard
To see robust data on Journey Builder emails, push messages, and SMS messages, access the Journey Analytics dashboard in your
Google Analytics-enabled Marketing Cloud account. When the Analytics integration is enabled, any user in your account can access
the dashboard in a journey.
Google Analytics Goals Tile
Google Analytics goals metrics are aggregated at the journey level in the Journey Analytics dashboard. The data provides insight
into how the journey contributes to the overall success of your marketing strategy. Get information about completed activities, such
as purchases and user engagement for website traffic generated by Marketing Cloud activities. You can configure the dashboard to
display up to five goals.
Google Analytics Delivery and Engagement Tiles
View Google Analytics email, SMS, and push message performance metrics aggregated at the journey level in the Journey Builder
Analytics dashboard. For example, see how subscribers in a journey are progressing from email to the web using email delivery rate,
unique open rate, and unique clicks. Monitor how email, SMS, and push message interactions drive the online behavior of subscribers
through live metrics. Metrics can include page views, bounce rate, goal completion, conversion rate, and average order value.
Google Analytics Conversions and Revenue Tiles
View Google Analytics ecommerce metrics, aggregated at the journey level, in the Journey Builder Analytics dashboard.
Google Analytics Traffic Tile
Gain insights that help you evaluate the impact of your marketing communications strategy. View Google Analytics site usage
metrics, aggregated at the journey level, in the Journey Builder Analytics dashboard.
Google Analytics Engagement and Views Tiles
Find out which marketing content is reaching your customers. Monitor the engagement that your messages are driving by checking
out Google Analytics views and engagement data on the Journey Analytics dashboard.

SEE ALSO:
Journey Analytics Dashboard

Journey Analytics Dashboard

Access unified cross-channel performance data in Journey Builder, and easily track your marketing campaign’s effectiveness. Journey
Analytics, powered by Google Analytics, unites Marketing Cloud SMS, push messaging, and email capabilities with Analytics behavioral
data in a single dashboard. You can compare how goals configured in Google Analytics perform over time, and you can see ecommerce,
messaging performance, and site usage data.
Track your marketing campaign’s effectiveness across views in your account for the date range you select. View and compare how goals
configured in Google Analytics perform, and compare data over different periods.
To use Google Analytics in a journey, link your Salesforce and Google Analytics accounts, and follow Google’s login process.

198
Marketing Cloud Einstein and Analytics Google Analytics Metrics

Considerations
• Any user in your account can access the Journey Analytics dashboard in a journey.
• When Google Analytics is enabled for your account, tracking is available by default in all journeys.
• When you create another version of a journey, it includes tracking even if Google Analytics was disabled when the journey was
created.
• The Journey Analytics data shown on the dashboard pertains to all versions of the journey and isn’t separated by journey version.
• Delivery rate is calculated by subtracting bounces from the number of total sends, and then dividing total sends by that number.
When there are no bounces, delivery rate is 100%.
The Goals component in Journey Analytics isn’t linked or related to Journey Builder goals or exit criteria. For more information on goals,
see Google Analytics help.

Use the Journey Analytics Dashboard

To see robust data on Journey Builder emails, push messages, and SMS messages, access the Journey Analytics dashboard in your Google
Analytics-enabled Marketing Cloud account. When the Analytics integration is enabled, any user in your account can access the dashboard
in a journey.
To use Analytics in a journey, link your Salesforce and Analytics accounts, and follow Google’s login process. Then enable Analytics
Tracking in Journey Settings, and add the domains whose UTM parameters you want to track. If you don’t add a domain, Analytics tracks
all domains that the journey’s links point to.

Note: The Goals component in Journey Analytics isn’t linked or related to Journey Builder goals or exit criteria.

1. To open the Journey Analytics dashboard, open a journey, and click .

2. Select the view to use.
3. To select a range of up to 30 days, click the date range. The date range must begin on or after the first day the journey is active.
You can also select another date range to compare to. The date ranges can’t overlap. The date range must begin on or after the first
day the journey is active. The maximum date range is 30 days. However, you can query the data for three years.
When you select a date range and compare it with a different date range, the rate of change appears in each dashboard tile.

4. Click .
5. To add or remove a view, click View.
6. To select up to five goals, click Goals.
7. To select accounts and properties, click GA4 Property.
8. Click Done.
9. To select data streams, click Data Streams.
10. Click Done.

Note: Changes made to components and their display order persist after you leave the journey.

11. To select email or mobile message metrics, click Filters.

12. Choose whether to show channel performance in aggregate or segregated by channel.
To change the components’ display order, drag each component to the desired position.

Tip: When SMS activities generate Google Analytics metrics, reporting doesn’t appear in the Content section. SMS messages don’t
include content assets or blocks.

199
Marketing Cloud Einstein and Analytics Google Analytics Metrics

Google Analytics Goals Tile

Google Analytics goals metrics are aggregated at the journey level in the Journey Analytics dashboard. The data provides insight into
how the journey contributes to the overall success of your marketing strategy. Get information about completed activities, such as
purchases and user engagement for website traffic generated by Marketing Cloud activities. You can configure the dashboard to display
up to five goals.
For more information, visit About goals.

Google Analytics Delivery and Engagement Tiles

View Google Analytics email, SMS, and push message performance metrics aggregated at the journey level in the Journey Builder
Analytics dashboard. For example, see how subscribers in a journey are progressing from email to the web using email delivery rate,
unique open rate, and unique clicks. Monitor how email, SMS, and push message interactions drive the online behavior of subscribers
through live metrics. Metrics can include page views, bounce rate, goal completion, conversion rate, and average order value.

Table 6: Common Metrics

Delivery Rate Number of sends minus number of bounces divided by the total
number of sends

Total Sent Number of times an email was sent

Table 7: Email Metrics

Total Opens Number of times subscribers render the images of an email in their
email client to preview emails without downloading images or
clicking a link

Unique Opens Number of times distinct users open an email and information
related to the first open for that user

Total Clicks Number of times an email link was clicked

Unique Clicks Number of times distinct users click a link and information related
to the first click for that user

Table 8: SMS Metrics

Undelivered Number of sends minus number of bounces

Total Clicks Number of times an SMS message was clicked

Push Metrics Number of sends

Direct Opens Number of times a user opens your app or website by tapping a
push message

Google Analytics Conversions and Revenue Tiles

View Google Analytics ecommerce metrics, aggregated at the journey level, in the Journey Builder Analytics dashboard.

200
Marketing Cloud Einstein and Analytics Google Analytics Integration FAQs

Analyze the impact of Marketing Cloud email and journey activities on customer conversion rates. Metrics include revenue, transactions,
average order value, and ecommerce conversion rate. For more information, visit About Ecommerce.

Google Analytics Traffic Tile

Gain insights that help you evaluate the impact of your marketing communications strategy. View Google Analytics site usage metrics,
aggregated at the journey level, in the Journey Builder Analytics dashboard.
View behavioral data for subscribers who visit your site through a link in a Marketing Cloud email, SMS, or push message. See how many
subscribers stayed and browsed your site, the number of pages they viewed, and how many subscribers abandoned browsing immediately.

Google Analytics Engagement and Views Tiles

Find out which marketing content is reaching your customers. Monitor the engagement that your messages are driving by checking
out Google Analytics views and engagement data on the Journey Analytics dashboard.
Use the Page or Screen Views tile on the Journey Analytics dashboard to see your most-visited web pages or screens.
Use the Engagement tile to visualize your customers’ engagement with email, SMS, and push messaging in a single chart
You can also compare the rate of change between time periods.

Google Analytics Integration FAQs

Review answers to frequently asked questions about the Google Analytics Integration with Marketing Cloud.

Why Can’t I See All the Accounts, Properties, and Views in the Google Analytics View Dropdown Menu in the Journey Analytics
Dashboard?
Only the accounts, properties, and views for which you are granted admin access appear in the Journey Analytics dashboard. To
edit user permissions, follow the instructions to configure Google Analytics 360 integration user permission.
I Purchased the Google Analytics 360 Integration, Why Can’t I See the Google Integration Admin Screen?
Confirm that you have Marketing Cloud and Google Analytics administrator roles. If you do not, complete the tasks to configure
them.
Is Google Analytics Data Stored in Marketing Cloud Data Extensions? Can I Use That Data in Other Parts of Marketing Cloud?
You cannot use the data in other parts of Marketing Cloud. This integration grants access to view your Google Analytics accounts,
properties, and views only in the dashboard.
The Journey Analytics Dashboard No Longer Shows Any Data from Google Analytics. Why?
The link created between your Google Analytics 360 and Marketing Cloud accounts can be revoked from the Google Analytics
account. It is possible that a Google Analytics account admin revoked the permissions you provided during set-up from Marketing
Cloud.
Why Can't I See My Google Analytics Accounts, Properties and Views in the Selector When I Link My User Account to Marketing
Cloud?
Administrator permissions are required to view the accounts, properties, and views associated with your Google account.
Does This Integration Comply with the Salesforce Privacy Policy?
Yes, when the track clicks feature is disabled for an email address, the Google Analytics UTM parameters do not append to the email.
Can I Determine Which Domains and Subdomains Are Tracked for Links Sent from My Journey?
Yes, you can allow one or more domains and subdomains using the allowlist in Journey Builder settings.

201
Marketing Cloud Einstein and Analytics Google Analytics Integration FAQs

Can I Define My Own Campaign Name Parameter for Links in an Email?

Yes. To enter a custom campaign name for each email activity in the Journey Builder email send flow, select the Set Per Message
option in the Google integrations tracking parameters.
What Happens If I Leave the Allowlist Domains Empty?
If no domains or subdomains are specified in the allowlist, the Google UTM tracking parameters are appended to all links.
What Level of Journey Data Is Displayed in the Journey Analytics Dashboard?
Data for all versions of the journey is aggregated by day and displayed in the dashboard.
If I Did Not Purchase the Google Analytics 360 Integration, Can I See the Journey Analytics Dashboard?
Yes. All Marketing Cloud users have access to email metrics in the Journey Analytics dashboard.
What Is the Earliest Selectable Date for the Date Filter on the Journey Analytics Dashboard?
The earliest selectable date is the date that version 1 of the journey was created. For example, if version 1 of the journey was created
more than 3 years before today's date, the earliest selectable date is 3 years before today.
How Far Back Can I Query My Google Analytics Data from the Journey Analytics Dashboard?
The last 3 years of Google Analytics data are available through this integration. For example, if you create the first version of the
journey three years and one month before today's date, the oldest data available is four years before today’s date.
What Is the Largest Selectable Date Range in the Date Filter?
The system defaults to the maximum of 30 days. If the journey started less than 30 days ago, the date range automatically adjusts
to a custom range to include the start date through today.
Can I Use Overlapping Date Ranges Using the Metric Compare Feature in the Date Filter?
No. Overlapping date ranges causes the system to count your data more than once and provides an inaccurate comparison of the
data sets.
How Are Deltas Calculated for the Metrics Compare Feature in the Journey Analytics Dashboard?
To calculate the comparison metric value, the system subtracts the comparison date range metric value from the date range metric
value.
Is There a Way to Simulate Contact Matching Between Google Analytics 360 and Marketing Cloud to Maximize Match Rates Quickly?
Yes. To identify a customer in an audience by matching the Client ID stored on the client machine in the GA cookie and the SFMC
ID, a session must be initiated by the user’s machine. You can only simulate a session and send a hit through Analytics 360’s
measurement protocol if you have both the Client ID and the SFMC ID to pass into the MP hit. Or you can send and email with a
CTA in the account welcome email the customer is receiving when they complete their online registration.
Can I Add the sfmc_id=%%subscriberid%% to a Link String in Journey Builder Manually?
Yes. You can manually append “sfmc_id=%%subscriberid%%” to a link string. This step allows the user to be added to an audience,
published to Marketing Cloud, and added back into a journey via the Analytics 360 event. You can also add the other utm parameters
if desired.
Is There a Way to Match and Remove Duplicate IDs in This Integration?
Yes. In Analytics 360, you can expose the Marketing Cloud SubscriberID as a custom dimension. When the Audiences integration
feature works, if there are multiple Google Client IDs with the same SubscriberID, the integration automatically deduplicates: the ID
before it is sent to Marketing Cloud.

Why Can’t I See All the Accounts, Properties, and Views in the Google Analytics View
Dropdown Menu in the Journey Analytics Dashboard?
Only the accounts, properties, and views for which you are granted admin access appear in the Journey Analytics dashboard. To edit
user permissions, follow the instructions to configure Google Analytics 360 integration user permission.

202
Marketing Cloud Einstein and Analytics Google Analytics Integration FAQs

I Purchased the Google Analytics 360 Integration, Why Can’t I See the Google
Integration Admin Screen?
Confirm that you have Marketing Cloud and Google Analytics administrator roles. If you do not, complete the tasks to configure them.
1. Assign a Role and Permissions to a Marketing Cloud User from the Users Screen.
2. Grant admin user permission for the Google Analytics 360 account.
3. Configure Google Analytics 360 Integration User Permission on page 196.

Is Google Analytics Data Stored in Marketing Cloud Data Extensions? Can I Use That
Data in Other Parts of Marketing Cloud?
You cannot use the data in other parts of Marketing Cloud. This integration grants access to view your Google Analytics accounts,
properties, and views only in the dashboard.

The Journey Analytics Dashboard No Longer Shows Any Data from Google Analytics.
Why?
The link created between your Google Analytics 360 and Marketing Cloud accounts can be revoked from the Google Analytics account.
It is possible that a Google Analytics account admin revoked the permissions you provided during set-up from Marketing Cloud.

Why Can't I See My Google Analytics Accounts, Properties and Views in the Selector
When I Link My User Account to Marketing Cloud?
Administrator permissions are required to view the accounts, properties, and views associated with your Google account.

Does This Integration Comply with the Salesforce Privacy Policy?

Yes, when the track clicks feature is disabled for an email address, the Google Analytics UTM parameters do not append to the email.

Can I Determine Which Domains and Subdomains Are Tracked for Links Sent from
My Journey?
Yes, you can allow one or more domains and subdomains using the allowlist in Journey Builder settings.

Can I Define My Own Campaign Name Parameter for Links in an Email?

Yes. To enter a custom campaign name for each email activity in the Journey Builder email send flow, select the Set Per Message option
in the Google integrations tracking parameters.

What Happens If I Leave the Allowlist Domains Empty?

If no domains or subdomains are specified in the allowlist, the Google UTM tracking parameters are appended to all links.

What Level of Journey Data Is Displayed in the Journey Analytics Dashboard?

Data for all versions of the journey is aggregated by day and displayed in the dashboard.

203
Marketing Cloud Einstein and Analytics Google Analytics Integration FAQs

If I Did Not Purchase the Google Analytics 360 Integration, Can I See the Journey
Analytics Dashboard?
Yes. All Marketing Cloud users have access to email metrics in the Journey Analytics dashboard.

What Is the Earliest Selectable Date for the Date Filter on the Journey Analytics
Dashboard?
The earliest selectable date is the date that version 1 of the journey was created. For example, if version 1 of the journey was created
more than 3 years before today's date, the earliest selectable date is 3 years before today.

How Far Back Can I Query My Google Analytics Data from the Journey Analytics
Dashboard?
The last 3 years of Google Analytics data are available through this integration. For example, if you create the first version of the journey
three years and one month before today's date, the oldest data available is four years before today’s date.

What Is the Largest Selectable Date Range in the Date Filter?

The system defaults to the maximum of 30 days. If the journey started less than 30 days ago, the date range automatically adjusts to a
custom range to include the start date through today.

Can I Use Overlapping Date Ranges Using the Metric Compare Feature in the Date
Filter?
No. Overlapping date ranges causes the system to count your data more than once and provides an inaccurate comparison of the data
sets.

How Are Deltas Calculated for the Metrics Compare Feature in the Journey Analytics
Dashboard?
To calculate the comparison metric value, the system subtracts the comparison date range metric value from the date range metric
value.

Example: Where the [Date Range Metric Value] is 56.25 and the [Comparison Date Range Metric Value] is 62.5 the calculation is
56.25% - 62.5% = - 6.25%

Is There a Way to Simulate Contact Matching Between Google Analytics 360 and
Marketing Cloud to Maximize Match Rates Quickly?
Yes. To identify a customer in an audience by matching the Client ID stored on the client machine in the GA cookie and the SFMC ID, a
session must be initiated by the user’s machine. You can only simulate a session and send a hit through Analytics 360’s measurement
protocol if you have both the Client ID and the SFMC ID to pass into the MP hit. Or you can send and email with a CTA in the account
welcome email the customer is receiving when they complete their online registration.

204
Marketing Cloud Einstein and Analytics Google Analytics Tracking

Can I Add the sfmc_id=%%subscriberid%% to a Link String in Journey Builder Manually?

Yes. You can manually append “sfmc_id=%%subscriberid%%” to a link string. This step allows the user to be added to an audience,
published to Marketing Cloud, and added back into a journey via the Analytics 360 event. You can also add the other utm parameters
if desired.

Is There a Way to Match and Remove Duplicate IDs in This Integration?

Yes. In Analytics 360, you can expose the Marketing Cloud SubscriberID as a custom dimension. When the Audiences integration feature
works, if there are multiple Google Client IDs with the same SubscriberID, the integration automatically deduplicates: the ID before it is
sent to Marketing Cloud.

Google Analytics Tracking

To get both web and mobile app metrics in the Journey Analytics dashboard, set up Google Analytics tracking for app and web. You
can then analyze how mobile app conversions impact web behavior.
Google Analytics now tracks your users’ online and mobile behavior using the GA4 property type. The new platform is a modern
event-based framework that uses first-party and Google data to analyze multiple sites and apps together.
In contrast to previous Google Analytics integrations, Marketing Cloud Setup now includes a Web URL Tracking and an App Event
Tracking string.
The GA4 Free version is available at no additional cost to Marketing Cloud customers with Journey Builder. Surface app and web conversion
events in context with native Journey metrics when you set up tracking for both app and web events.

Configure Google Analytics App Tracking

To track the URLs used in supported mobile activities in this business unit, set up Google Analytics 4 (GA4) property tracking.
Configure Google Analytics Web Tracking
To track the URLs used in Journey Builder emails and SMS activities in this business unit, set up Google Analytics 4 (GA4) property
tracking.

Configure Google Analytics App Tracking

To track the URLs used in supported mobile activities in this business unit, set up Google Analytics 4 (GA4) property tracking.
Before you can set up tracking for supported mobile apps, ask your developer to configure the Firebase SDK, which supports logging
Marketing Cloud custom Campaign details to GA4.
1. In Marketing Cloud, navigate to Data Management, and click Parameter Management.
2. Click GA4 Property Tracking.
3. On the App tab, click the toggle to enable the tracking parameters.

Note: You can’t configure the tracking parameters.

4. Click Save.

Configure Google Analytics Web Tracking

To track the URLs used in Journey Builder emails and SMS activities in this business unit, set up Google Analytics 4 (GA4) property tracking.

205
Marketing Cloud Einstein and Analytics Use Einstein to Improve Your Marketing Efforts

1. In Marketing Cloud, navigate to Data Management, and click Parameter Management.

2. Click GA4 Property Tracking.
3. On the Web tab, click the toggle to enable the tracking parameters.

Note: You can’t configure the tracking parameters.

4. Click Save.

Use Einstein to Improve Your Marketing Efforts

AI for Marketing provides insights and data to inform the content and timing of your marketing activities. Use powerful Einstein features
to understand the engagement and behaviors of your customers so you can personalize every interaction.

Your Guide to AI for Marketing

Get Started with Einstein Find Einstein Use Cases Set Up and Maintain

Salesforce Help: Feature Overview and Salesforce Help: Explore Marketing Cloud Trailhead: Marketing Cloud Einstein
Requirements Einstein Solutions Activation: Quick Look

Salesforce Help: Email Client Privacy Changes Trailhead: Artificial Intelligence for Marketers PDF Guide: Marketing Cloud Personalization
Builder and Einstein Recommendations
Implementation Guide

Salesforce Help: Understand the Data Trailhead: Artificial Intelligence for Social Salesforce Developer: Einstein REST APIs
Media

Trailhead: Einstein for Marketing Cloud Trailhead: Artificial Intelligence for Salesforce Developer: Authentication through
Basics Advertisers Marketing Cloud OAUTH

Salesforce Developer: Marketing Cloud

Einstein Overview

206
Marketing Cloud Einstein and Analytics Use Einstein to Improve Your Marketing Efforts

Automate Content Personalization Automate Recommendations Find the Right Audience at the Right
Time

Salesforce Help: Einstein Content Tagging Salesforce Help: Einstein Email Salesforce Help: Einstein Send Time
Recommendations Optimization

Salesforce Help: Einstein Content Selection Salesforce Help: Einstein Web Salesforce Help: Einstein Engagement
Recommendations Scoring

Trailhead: Einstein Content Selection Basics Salesforce Developer: Einstein Salesforce Help: Einstein Engagement
Recommendations API Frequency

Trailhead: Einstein Content Selection Video: Einstein Web Recommendations Trailhead: Einstein Send Time and Frequency
Solutions Optimization

Video: Einstein Content Selection Trailhead: Einstein Email and Web Trailhead: Einstein Engagement Scoring in
Recommendations Marketing Cloud

Salesforce Developer: Introduction to Einstein Video: Einstein Email Recommendations Video: Einstein Send Time Optimization
Content Selection APIs Setup Wizard

Video: Admin Best Practices: Introducing Video: Personalization Made Simple with
Einstein Recommendation Builder Einstein Engagement Frequency

Gain Content Insights Einstein for Marketing Model Cards Global Data Usage & Learn More

Salesforce Help: Einstein Copy Insights Salesforce Help: Einstein Engagement Salesforce Help: Einstein and Data Usage in
Frequency Model Card Marketing

Salesforce Help: Einstein Messaging Insights Salesforce Help: Einstein Engagement Salesforce Help: Global Model Data
Scoring for Email Model Card

Video: Einstein Messaging Insights Salesforce Help: Einstein Engagement Salesforce Help: A Marketer's Guide to the
Scoring for Mobile Model Card Trusted Use of Einstein

Trailhead: Einstein Messaging Insights: Quick Salesforce Help: Einstein Messaging Insights Salesforce Blog: Responsible AI in Marketing:
Look Model Card Embedding Ethics by Design

Salesforce Help: Einstein Send Time Salesforce: AI Revolution (Download)

Optimization for Email Model Card

Salesforce Help: Einstein Send Time Video: Optimizing Your Mobile App Push
Optimization for Mobile Model Card Notifications with Einstein and Datorama
Reports

207
Marketing Cloud Einstein and Analytics Use Einstein to Improve Your Marketing Efforts

Salesforce Help: Einstein Subject Line Tester Video: Einstein for Marketing Cloud: Single
Model Card Send Journeys

Salesforce Help: Einstein Probabilistic Opens

Model Card

Salesforce Help: Einstein Content Selection

and Testing Model Card

Salesforce Help: Einstein Email and Web

Recommendations Model Card

Marketing Cloud Einstein Updates for Email Client Privacy Changes

Some email client providers are making privacy changes that could impact open rate metrics and calculations. Salesforce is updating
several of the Marketing Cloud Einstein apps to account for the privacy changes. Trust is the #1 Value at Salesforce. Privacy and
security continue to become more important in our digital lives. Our top priority is to create the solutions that help you respond,
act, and succeed in these new environments. Marketers traditionally create automations, campaign engagement strategies, and
more based on email opens since they could signal whether a customer or prospect is interested in your content. Because of the
new privacy options available to customers, email opens are likely to be a less reliable engagement signal.
Einstein for Marketing Cloud Feature Overview and Requirements
Find out if Marketing Cloud for Einstein is right for your business.
Explore Marketing Cloud Einstein Solutions
Add AI to your marketing efforts without adding guesswork. Use Einstein Overview and Learning Center to review important key
performance indicators for individual applications. And see how Einstein for Marketing can help your marketing organization solve
common use cases with better results.
Understand the Data Einstein Uses
Providing Einstein with good data makes it more likely for marketers to get good predictions. Use data quality scores to understand
the quality of the data that each Einstein app requires to generate predictions, insights, analytics, and more. Find data quality metrics
on each Einstein app dashboard and Einstein Overview card.

1
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

208
Marketing Cloud Einstein and Analytics Use Einstein to Improve Your Marketing Efforts

Einstein Engagement Scoring

Einstein Engagement Scoring predicts consumer engagement with email and MobilePush messaging. It uses customer data and
machine learning to generate predictive models that assign scores for every contact’s likelihood to engage with emails and interact
with push notifications.
Einstein Messaging Insights
Einstein Messaging Insights alerts you to changes in your marketing performance no matter where you are in the Marketing Cloud.
The Einstein notifications badge appears in the header, where it’s constantly accessible to let you know how your email sends and
journeys perform. When an anomaly occurs, the notifications badge alerts you. Navigate to the insights hub for more information
about quantifying your results.
Einstein Send Time Optimization
Marketing Cloud Einstein Send Time Optimization (STO) determines the best time to send a message. Using machine learning,
Einstein predicts optimal send times so that a user is likely to engage with your message.
Einstein Engagement Frequency
Avoid a lack of awareness from too few messages or burnout from too many messages. Einstein Engagement Frequency in Marketing
Cloud evaluates your contacts and subscribers and identifies the optimal number of email messages to send.
Einstein Copy Insights
Einstein Copy Insights uses text analytics and natural language processing to analyze the text from your commercial email subject
lines to uncover language insights. Use these insights to craft subject lines that drive stronger email engagement. With the performance
tester you can find out how your subject line is likely to affect a message’s engagement rate by comparing it to past subject lines
and their engagement rates. You can evaluate a single subject line or compare up to 10 different subject lines.
Einstein Content Selection
Einstein Content Selection is a no-code, open-time experimentation tool for personalized content. Because Einstein selects content
at open time, it continues to evaluate for winning content while also experimenting to ensure that click-through rates are optimized.
Einstein Content Testing
To optimize engagement, quickly test images in Einstein Content Testing. For more complex personalized targeting, use Einstein
Content Selection, which includes fatigue rules and targeted content based on user preferences.
Einstein Content Tagging
Einstein Content Tagging automatically applies searchable tags to image files in your Marketing Cloud account. You can tell Einstein
to add up to 25 tags per image. Einstein tags existing JPG, JPEG, and PNG files that are 10 MB or less.
Einstein Email Recommendations
Use Einstein Email Recommendations to observe customer behavior, build preference profiles, and deliver the next-best content or
product. You can also refine recommendations to match your business rules. Recommendation content surfaces in placeholders for
recommendations on your website.
Einstein Email and Web Recommendations Model Card
The model in this card analyzes and provides personalized product and content recommendations.
Einstein Web Recommendations
Einstein Web Recommendations use Einstein's capabilities to observe behavior, build preference profiles, and deliver the next-best
personalized content to each website visitor. Use scenarios within the application to refine recommendations to match your specific
business rules. Predictive Content is surfaced in placeholders for recommendations on your website.
A Marketer's Guide to the Trusted Use of Einstein
Salesforce believes that the benefits of AI can be accessible to everyone. But increasingly, AI is facing a crisis of trust.

209
Marketing Cloud Einstein and Analytics Marketing Cloud Einstein Updates for Email Client Privacy
Changes

Marketing Cloud Einstein Updates for Email Client Privacy Changes

Some email client providers are making privacy changes that could impact open rate metrics and calculations. Salesforce is updating
several of the Marketing Cloud Einstein apps to account for the privacy changes. Trust is the #1 Value at Salesforce. Privacy and security
continue to become more important in our digital lives. Our top priority is to create the solutions that help you respond, act, and succeed
in these new environments. Marketers traditionally create automations, campaign engagement strategies, and more based on email
opens since they could signal whether a customer or prospect is interested in your content. Because of the new privacy options available
to customers, email opens are likely to be a less reliable engagement signal.
In your Marketing Cloud Einstein apps, we're making several updates now as outlined in the table, and over subsequent releases, to help
ensure your data, insights, and predictions are as accurate and reliable as possible. We’re moving away from solely using traditional open
rate metrics. Instead, we’re moving to an engagement rate metric that includes a blend of additional signals, including clicks, combined
with open rate metrics that give you a more holistic view of your customers' engagement with your content.

Table 9: Einstein App Updates

Einstein App Details
Einstein Send Time The model now uses an engagement rate instead of solely an open rate to determine the most optimal
Optimization send time for a more nuanced metric to ensure more accuracy.

Einstein Copy Insights Einstein Copy Insights uses the engagement rate instead of solely an open rate to generate language
insights and predict future performance.

Einstein Messaging Insights Open rates reported in Einstein Messaging Insights could be less reliable as a result of the privacy
updates. Einstein Messaging Insights can still detect open rate insights because the model uses relative
changes.

Einstein Engagement The model uses an engagement rate and unsubscribe rate instead of solely an open rate for a more
Frequency nuanced metric, providing more accuracy.

Einstein Engagement Scoring The model uses an engagement rate for personas instead of an overlap between open and click rate.
We’re updating metrics calculations in Einstein Engagement Scoring to increase reliability as a result
of the privacy updates.

Related Content

Email Client Privacy and Non-Subscriber Activity in Marketing Cloud Email and Journeys

Salesforce Marketing Cloud & iOS 15 Updates Webinar on Apple Privacy

Apple’s Privacy Changes Will Force Marketers to Innovate - Here’s Where to Start

Marketing and Consumer Privacy

210
Marketing Cloud Einstein and Analytics Marketing Cloud Einstein Updates for Email Client Privacy
Changes

Einstein Probabilistic Opens Model Card

The model in this card analyzes how open events are calculated and the likelihood that each open event is real.

Einstein Probabilistic Opens Model Card

The model in this card analyzes how open events are calculated and the likelihood that each open event is real.

Model Details
The Marketing Cloud Einstein Probabilistic Opens model analyzes message open likelihood using these training algorithms, parameters,
fairness constraints, features, and other applied approaches.
Intended Use
The Marketing Cloud Einstein Probabilistic Opens model is intended for these use cases.
Relevant Factors
These factors are associated with the Marketing Cloud Probabilistic Opens model.
Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance
measures are associated with the Einstein Probabilistic Opens model.
Training Data
You have a customized version of the model that’s trained on your data alone. Data from one Salesforce customer doesn’t affect the
behavior for another Salesforce customer. While model training happens for each customer on their data, the initial development
of the model is validated with a representative set of pilot customers’ data.
Ethical Considerations
Review the ethical factors associated with the Marketing Cloud Einstein Probabilistic Opens model. To avoid bias and other ethical
risks, the Einstein Probabilistic Opens model doesn’t include demographic data.

Model Details
The Marketing Cloud Einstein Probabilistic Opens model analyzes message open likelihood using these training algorithms, parameters,
fairness constraints, features, and other applied approaches.

Person or Organization
Salesforce Marketing Cloud Einstein

Model Date and Version

• December 2021
• Minor changes can occur throughout the release.
• Major changes can occur and are communicated via release notes.

Model Type
Time-series analysis, Predictive modeling

211
Marketing Cloud Einstein and Analytics Marketing Cloud Einstein Updates for Email Client Privacy
Changes

General Information
Einstein Probabilistic Open assigns each email open event a confidence score that represents the event being a human-initiated real
open. The score ranges from 0% to 100%. Higher scores represent higher confidence that the open is real. Lower scores represent a
higher chance that the open event is machine-generated.
The model analyzes a subscriber’s historical events and engagement patterns to predict the chance that an open is real. The model
performs event association and attribution to monitor behavior changes. Most recent behavior changes and engagement patterns are
emphasized more heavily in the predictions.
Compared to a typical filtering-based approach, probabilistic opens provides more accurate results by reducing the risk of false positive
and false negative results while minimizing information loss. Probabilistic opens are foundational to all other Einstein modeling and
products. Einstein trains each customer’s model using only that customer’s data.

Constraints
There are no discernible constraints.

License
Einstein Probabilistic Opens is available to Salesforce Marketing Cloud customers with any of these editions.
• Corporate Edition
• Enterprise Edition
• Enterprise+ Edition

Questions or Comments
Send questions or comments about the model to mce-support@salesforce.com.

Intended Use
The Marketing Cloud Einstein Probabilistic Opens model is intended for these use cases.

Primary Intended Uses

• The Einstein Probabilistic Open model provides a layer of information that helps Einstein calculate how trustworthy each email open
is. This model is in response to Mail Privacy Protection implemented by some email client providers. As a result, Einstein can build
more accurate models and provide better recommendations.
• Marketers can gain insights from Einstein Probabilistic Opens that provide a more realistic view of subscriber engagement levels.
Using this insight, marketers can conduct further segmentation or better targeting on future campaigns.

Out-of-Scope Use Cases

Anything other than the primary use case is out of scope and not recommended.

Relevant Factors
These factors are associated with the Marketing Cloud Probabilistic Opens model.

212
Marketing Cloud Einstein and Analytics Marketing Cloud Einstein Updates for Email Client Privacy
Changes

Model Input
Einstein Engagement Frequency analyzes up to 90 days of historical engagement patterns of the subscribers. The engagement history
includes these factors.
• Email sends, bounces, and engagement events including open, click, and unsubscribe, spam complaints, and associated timestamps
• Data and metadata about customer sending patterns, including how campaigns are executed
The engagement history that Einstein Probabilistic Open analyzes excludes these factors.
• Data purchased or collected from third parties
• Demographic Data, which is typically stored in SFMC as data extensions or subscriber or contact attributes
• Specific content in the email template or rendered email body

Model Output
For each open event, a probabilistic score is produced to measure the likelihood that the open is real.

Groups
The model doesn’t include demographic data or other data purchased from third-party data providers.

Environment
The model is trained and deployed in the Salesforce Marketing Cloud environment.

Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance measures
are associated with the Einstein Probabilistic Opens model.

Model Performance Measures

Model performance metrics include data like model mean absolute error score.

Training Data
You have a customized version of the model that’s trained on your data alone. Data from one Salesforce customer doesn’t affect the
behavior for another Salesforce customer. While model training happens for each customer on their data, the initial development of the
model is validated with a representative set of pilot customers’ data.

Ethical Considerations
Review the ethical factors associated with the Marketing Cloud Einstein Probabilistic Opens model. To avoid bias and other ethical risks,
the Einstein Probabilistic Opens model doesn’t include demographic data.
As you interpret your data, be aware of making assumptions based on the scores generated. Scenarios with potential adverse outcomes
can occur in certain circumstances.

Example: For example, the model predicts low engagement so you choose not to send a marketing communication to a set of
customers. If the prediction was erroneous, there could be negative impact to excluding some of those customers from access to
benefits or opportunities.

213
Marketing Cloud Einstein and Analytics Einstein for Marketing Cloud Feature Overview and
Requirements

Einstein for Marketing Cloud Feature Overview and Requirements

Find out if Marketing Cloud for Einstein is right for your business.
Einstein for Marketing Cloud uses Salesforce's AI to help you best evaluate and implement your marketing activities. Use valuable insights
on audiences, send time, engagement frequency, and your content to best target your customers. Deliver information to your customers
when they need it and how they need it.
Einstein in Marketing Cloud offers a range of opportunities for you to analyze, automate, and optimize your content. Use the apps
throughout Marketing Cloud platforms to gain insight and better target your audiences.
These Marketing Cloud platforms feature Einstein for Marketing Cloud:

Cloud Product Compatibility (Editions)

Messaging and Journeys (M&J) Professional (Add On)
Corporate
Enterprise
Enterprise+

Marketing Cloud Account Engagement Advanced and Premium editions

Customer Data Platform Dependent on M&J edition

To take advantage of Einstein features use the following engagement history:

Threshold Days of Historical Data

Minimum 7

Recommended 28

Optimal 90

Key Marketing Operations Served by Einstein for Marketing Cloud

Smart Segmentation
• Einstein Engagement Scoring predicts consumer engagement with email and mobile push messaging. It uses customer data and
machine learning to generate predictive models that assign scores to a contact’s likelihood to engage with emails.
Smart Orchestration
• Einstein Send Time Optimization (STO) determines the best time to send an email or push notification.
• Einstein Engagement Frequency evaluates your contacts and identifies the optimal number of email messages or push notifications
to send. Avoid a lack of awareness from too few messages or burnout from too many messages.
Smart Content
• Einstein Copy Insights analyzes the text from your email subject lines to uncover language insights. Use these insights to craft subject
lines that drive stronger email engagement.
• Use Einstein Content Selection to send personalized content to each customer when they engage with your messages. You supply
Einstein with content assets, and Einstein selects the best content for each contact based on their profile and category affinity.

214
Marketing Cloud Einstein and Analytics Explore Marketing Cloud Einstein Solutions

Explore Marketing Cloud Einstein Solutions

Add AI to your marketing efforts without adding guesswork. Use Einstein Overview and Learning Center to review important key
performance indicators for individual applications. And see how Einstein for Marketing can help your marketing organization solve
common use cases with better results.
Einstein Overview cards show a snapshot of each Einstein app. Click Details to flip to the details on the back of the card. Details provide
a summary of how each Einstein application uses your data. It shows which channels and parts of Marketing Cloud the app supports
and the workflows that it’s designed to help you optimize. A single app can support multiple channels, workflows, and applications. But
not every feature in the app supports everything indicated on the card. Consult feature-specific considerations for details.
In the Data section, you can see whether the app uses data from individual Business Units, data from all Business Units in your Enterprise,
or Global data.
The Channels section shows whether the app works with Email, MobilePush, or both.
Workflow Types show the types of workflows the selected Einstein app supports including Content Creation, Data Augmentation,
Orchestration, Insight Generation, and Segmentation.
The Application Support section shows which Marketing Cloud applications work with the selected Einstein app. Most apps work with
Journey Builder. But these other Marketing Cloud apps can also work with various Einstein apps.
• Content Builder
• Mobile Studio
• Email Studio
• Automation Studio
Einstein Learning Center is an interactive, educational, use-case-driven portal that links Einstein apps and features directly to real marketing
key performance indicators (KPIs). In-app links to IdeaExchange and the Trailblazer Community make it easy to engage, collaborate, and
share ideas with other marketers.
In the Marketing Cloud navigation, find the Einstein Learning Center by clicking Einstein Learning Center, then Overview. Use an
application’s overview card to explore primary KPIs or navigate to the app directly. In Learning Center, select a use case card in the ribbon
at the bottom to review how Einstein solves it.
With Einstein Send Time Optimization you can preview the best send times for a data extension that you plan to use for sending. Click
Preview in the Einstein Learning Center to get started.

You can collapse or expand the Learning Center by clicking in the banner.

Preview Einstein’s Optimal Send Times

Find out when Einstein would send for contacts in any data extension. Select any data extension, set the sending window, and get
a preview of optimal send times that Einstein identifies for your contacts. When a data extension has numerous rows, previews are
based on sampling data.

SEE ALSO:
Understand the Data Einstein Uses

Preview Einstein’s Optimal Send Times

Find out when Einstein would send for contacts in any data extension. Select any data extension, set the sending window, and get a
preview of optimal send times that Einstein identifies for your contacts. When a data extension has numerous rows, previews are based
on sampling data.

215
Marketing Cloud Einstein and Analytics Understand the Data Einstein Uses

After you build a preview, it takes time to build before you see its results. In most cases, a data extension preview is built within a few
minutes. Check the progress indicator next to your preview to estimate how long it takes to build the preview.
When the data extension that a preview is based on is deleted, the preview is removed from the list after 90 days.
1. Select Einstein in the Marketing Cloud top navigation.
2. Click Einstein Overview
3. Click Preview.
4. Select a data extension.
5. Set a sending time frame.
6. Click Done.
Building the preview starts. You can navigate away while the build is in progress, then return to see results.
7. When the progress indicator reads Complete, click the preview to see a graph showing the optimal sending hours that Einstein
identifies for this data extension’s contacts.

Refresh a Send Time Preview

After you create a preview of a data extension, you can refresh it to find out if Einstein’s optimal send times have changed.
Delete a Send Time Preview
When a preview is no longer useful, you can delete it.

SEE ALSO:
Einstein Send Time Optimization for Journey Builder

Understand the Data Einstein Uses

Providing Einstein with good data makes it more likely for marketers to get good predictions. Use data quality scores to understand the
quality of the data that each Einstein app requires to generate predictions, insights, analytics, and more. Find data quality metrics on
each Einstein app dashboard and Einstein Overview card.
Considerations
• Achieving a 100% data quality score isn’t the objective. Instead, use your current score as a benchmark for future results. When your
data score is above the minimum threshold, you’re likely to see benefits from AI.
• The longer Einstein is enabled and learning, the better your results are likely to be. Each Einstein app is unique, but most apps can
deliver results within 90 days.
• AI works best when it has lots of data to analyze. Using global data models boosts the amount of data used for making predictions.
Global models safely harness the power of the Salesforce ecosystem to provide more accurate, actionable results.

Note: Transactional sends and test sends are excluded when generating your data quality score.

Einstein and Data Usage in Marketing

Marketing Cloud Einstein is built on data. As an Einstein customer, it’s important for you to know what data is being used in your
Einstein products. This table lists the data that is used by each feature.

216
Marketing Cloud Einstein and Analytics Understand the Data Einstein Uses

Global Model Data Opt In and Opt Out

Einstein intelligence is built on data. The more data Einstein has, the more powerful the resulting predictions. Most organizations
don’t have enough data to build their own models. To give customers more meaningful AI, we build global predictive models that
customers can use. Global models look for aggregate, anonymous trends across many Salesforce customers, so the first step is to
gather data from multiple Salesforce orgs.
Gauge Your Einstein Engagement Scoring Data Quality
Check your mobile app’s data quality score for insight about the engagement data that Einstein uses to predict your customers’
likelihood to engage. Data quality scores for Einstein Engagement Scoring are generated at the mobile app level only.
Gauge Your Einstein Engagement Frequency Data Quality
Check your data quality score for insight about the engagement data that Einstein uses to predict your customers’ likelihood to
engage. Data quality scores for Einstein Engagement Frequency are generated at the business unit level only.
Gauge Your Einstein Send Time Optimization Data Quality
Check your Enterprise’s data quality score for insight about the engagement data that Einstein uses to predict optimal send times.
Data quality scores for Einstein Send Time Optimization are generated at the Enterprise level only.
Data Residency
If your organization uses Hyperforce, Einstein may process data outside your geographical location.

SEE ALSO:
Evolve Your Marketing Strategy with Artificial Intelligence

Einstein and Data Usage in Marketing

Marketing Cloud Einstein is built on data. As an Einstein customer, it’s important for you to know what data is being used in your Einstein
products. This table lists the data that is used by each feature.
The table lists both the Customer Data that is used, which is data submitted by the Customer to our services as defined in our Main
Services Agreement (MSA), and the usage data that is used, which is data relating to users interactions with Salesforce. Data submitted
to an Einstein feature may be used to train AI models, to improve your services and features, or to develop new features that you’ll have
access to without additional cost.
The table also indicates which features use global models, which are models that look for aggregated, anonymous trends across multiple
Salesforce Customers. The Customer has control over whether their data contributes to global models. For more information on how
to control how your data is used, see Global Model Data Opt-In and Opt-Out on page 219 for Marketing Cloud.

Cloud or Package Feature Data Used Global Model Used

Marketing Cloud Send Time Email Engagement (email sends, opens, clicks, Yes - optional
Einstein for Optimization for unsubscribes, bounces, spam complaints),
Engagement Email Customer sending pattern data and metadata,
Email address (anonymized when using global
models

Send Time App Engagement (Push, TapOpen, AppOpen, No

Optimization for TimeInApp), Customer sending pattern data and
Mobile metadata

Engagement Email Engagement (email sends, opens, clicks, Yes - optional

Scoring for Email unsubscribes, bounces, spam complaints),
Customer sending pattern data and metadata,

217
Marketing Cloud Einstein and Analytics Understand the Data Einstein Uses

Cloud or Package Feature Data Used Global Model Used

User Retention and Subscription History,
Subscriber web interaction events (view, search,
profile, and purchase), customer-defined
categorization thresholds, Email address
(anonymized when using global models)

Engagement App Engagement (Push, TapOpen, AppOpen, Yes - optional

Scoring for Mobile TimeInApp),

Customer sending pattern data and metadata,

customer-defined categorization thresholds

Engagement Email Engagement (email sends, opens, clicks, No

Frequency unsubscribes, bounces, spam complaints),
Customer sending pattern data and metadata,
Subscriber ID

Product Behavioral Data (pageviews, carts, conversions, No

Recommendations categories, wishlists), recommendation
(Email) engagement (recommendation views, clicks,
carts, purchases), and User Attributes provided
through Collect.js

Product Behavioral Data (pageviews, carts, conversions, No

Recommendations categories, wishlists), recommendation
(Web) engagement (recommendation views, clicks,
carts, purchases), and user attributes provided
through Collect.js

Content Selection Email Engagement (email sends, No

opens/selections, clicks), optional start-end
dates, optional simple rules that exclude assets
based on meta-data or previous selections for
subscribers.

Content Testing Email Engagement (email sends, opens, clicks) No

Content Tagging Images No

Subject Line Tester Email Engagement (email sends, opens, clicks, Yes - required
unsubscribes, bounces, spam complaints),
subject lines

Copy Insights Email Engagement (email sends, opens, clicks, No

unsubscribes, bounces, spam complaints),
subject lines

Messaging Insights Email Engagement (email sends, opens, clicks, No

unsubscribes, bounces, spam complaints),
Customer sending pattern and campaign data
and metadata (for example, batch sends,
Journey Builder sends, Automation Studio sends,

218
Marketing Cloud Einstein and Analytics Understand the Data Einstein Uses

Cloud or Package Feature Data Used Global Model Used

transactional sends, triggered sends, past and
future automations), subject lines

Probabilistic Email Engagement (email sends, opens, clicks, No

Opens unsubscribes, bounces, spam complaints),
Customer sending pattern data and metadata

Global Model Data Opt In and Opt Out

Einstein intelligence is built on data. The more data Einstein has, the more powerful the resulting predictions. Most organizations don’t
have enough data to build their own models. To give customers more meaningful AI, we build global predictive models that customers
can use. Global models look for aggregate, anonymous trends across many Salesforce customers, so the first step is to gather data from
multiple Salesforce orgs.

What Are Global Models?

Currently, most Salesforce Einstein features build a unique predictive model based on each customer’s own Salesforce data. This
single-customer model is great for features that don’t require much data, but some models require more data than any single customer
can provide. Global models combine data from multiple Salesforce orgs to create a predictive model that can be used by many. Even if
you have enough data to create a single-customer model, there are times when a global model provides better predictions.
When it’s enabled in your Enterprise, you can get better predictions by incorporating data from Marketing Cloud’s global data pool. As
a result, predictions are more accurate and can cover more contacts in your Enterprise, leading to better engagement rates. In Einstein
Setup, you can control whether to participate in global models.

Data Usage
The Einstein features that can use global data modeling to improve your predictions have corresponding model cards to provide details
about data usage. For more details, see Einstein and Data Usage in Marketing on page 217. When you participate in the global model,
all identifiable data for contacts added to the global pool is removed, and no customer data is shared with other enterprises.

How Do Global Models Impact My Data?

If your Salesforce data is included in global models, rest assured that nothing changes in terms or security, privacy, or data residency.
Your data stays in our trusted environment, described in the Marketing Cloud Einstein Trust and Compliance Documentation. When
applied to Einstein features, global models never cause any of your data, including confidential information, to be shared with other
customers. How can we be so sure? Because global models work by looking for aggregate, anonymous trends from multiple sources.

Opt Out
You can opt out to exclude your data from Salesforce Marketing Cloud Einstein global data models. Marketing Cloud admins can set the
participation or opt-out of global models in Marketing Cloud Setup as shown. Salesforce doesn’t use your customer data for research
and development of new services or features, and no Salesforce employee can view your customer data outside of a support case, pilot,
or as otherwise described in your legal agreements. Your anonymized data is only used in the global pool in Einstein features for which
you choose to participate in global model usage. Opt-outs are controlled at the Enterprise ID (EID) level.

219
Marketing Cloud Einstein and Analytics Understand the Data Einstein Uses

Example:

SEE ALSO:
Activate Einstein Send Time Optimization
Salesforce Einstein: Global Model Opt-Out Process

Gauge Your Einstein Engagement Scoring Data Quality

Check your mobile app’s data quality score for insight about the engagement data that Einstein uses to predict your customers’ likelihood
to engage. Data quality scores for Einstein Engagement Scoring are generated at the mobile app level only.
Each mobile app’s data quality score is generated by analyzing the app’s engagement data. This analysis determines a Pattern Predictability
score and a Data Maturity score.
• To determine the Pattern Predictability score, Einstein analyzes the distinctness of your customers’ engagement patterns with your
mobile app. Greater pattern predictability leads to more accurate predictions of future engagement behavior. When your messages
are more compelling and drive higher engagement rates, your Pattern Predictability score is higher. When your engagement rates
are lower, your Pattern Predictability score is lower. Pattern Predictability differs from engagement rate because it evaluates engagement
events as they correlate to one another throughout your customers’ engagement history.
• To determine the Data Maturity score, Einstein analyzes the length of time that each of your customers has had data available to
make predictions, and how much data is available. This score helps Einstein understand how sensitive your subscribers are to changes
in your sending patterns over time. When you have a greater history of data for each of your customers, your Data Maturity score is
higher.
To find your data quality score, navigate to the Einstein Engagement Scoring for MobilePush dashboard. To see your scores and tips that
can help raise your data quality score, click Data Quality Score.

Note: Transactional sends and test sends are excluded when generating your data quality score.

SEE ALSO:
Einstein Engagement Scoring for Mobile Model Card
Evolve Your Marketing Strategy with Artificial Intelligence

Gauge Your Einstein Engagement Frequency Data Quality

Check your data quality score for insight about the engagement data that Einstein uses to predict your customers’ likelihood to engage.
Data quality scores for Einstein Engagement Frequency are generated at the business unit level only.

220
Marketing Cloud Einstein and Analytics Understand the Data Einstein Uses

Each business unit’s data quality score for email is generated by analyzing the business unit’s engagement data. This analysis determines
a Frequency Density score and an Engagement Frequency Rate score.
• To determine the Frequency Density score, Einstein analyzes the different cadences of sending frequencies in your business unit,
comparing the areas of highest concentration of this business unit’s sending frequencies to the maximum sending frequency in
your account. When you send messages to different customer segments at different cadences, you create a variety of send frequencies.
To generate engagement frequency scores send to at least five customer segments.
• To determine the Engagement Frequency Rate score, Einstein analyzes how often contacts in your business unit engage with a
message that’s part of a distinct sending frequency. Einstein compares this rate to the number of sending frequencies that the same
contact has experienced. This score helps Einstein understand how your contacts engage with emails across different sending
frequencies.
To find your data quality score, navigate to the Einstein Engagement Frequency dashboard. To see your scores and tips that can help
raise your data quality score, click Data Quality Score.

Note: Transactional sends and test sends are excluded when generating your data quality score.

SEE ALSO:
Einstein Engagement Frequency Model Card
Evolve Your Marketing Strategy with Artificial Intelligence

Gauge Your Einstein Send Time Optimization Data Quality

Check your Enterprise’s data quality score for insight about the engagement data that Einstein uses to predict optimal send times. Data
quality scores for Einstein Send Time Optimization are generated at the Enterprise level only.
Each Enterprise’s data quality score for email is generated by analyzing the Enterprise’s engagement data. This analysis determines a
send time coverage score and a data richness score. On the Einstein Send Time Optimization (STO) dashboard for mobile, the send time
coverage score is replaced with a mobile send coverage score.
• To determine the send time coverage score and mobile send coverage score, Einstein analyzes the number of hours in a week during
which you have at least one send. When your sends are spread across more hours during the week, your send time coverage score
is higher. When your sends happen during fewer hours, your send time coverage score is lower.
• To determine the data richness score, Einstein analyzes the amount and quality of engagement data that’s used to make predictions
for each individual contact. Einstein analyzes only mobile send data to determine the mobile data richness score and only email
send data to determine email data richness.
To find your data quality score, navigate to Einstein Send Time Optimization and view the dashboard. To see your scores and tips that
can help raise your data quality score, click Data Quality Score.

Note: Transactional sends and test sends are excluded when generating your data quality score.

SEE ALSO:
Einstein Send Time Optimization for Email Model Card
Evolve Your Marketing Strategy with Artificial Intelligence

Data Residency
If your organization uses Hyperforce, Einstein may process data outside your geographical location.

221
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

Example: Your organization in India is on Hyperforce. You enable Einstein features to help you identify the best time to send
messages to your customers. Your Einstein data is processed in data stacks in Europe.

Einstein Engagement Scoring

Einstein Engagement Scoring predicts consumer engagement with email and MobilePush messaging. It uses customer data and machine
learning to generate predictive models that assign scores for every contact’s likelihood to engage with emails and interact with push
notifications.
Einstein Engagement Scoring is included with Corporate and Enterprise Edition or available as an add-on purchase to Pro Edition. For
customers that purchased a Corporate or Enterprise Edition before October 27, 2017, Einstein Engagement Scoring is available at no
additional charge upon execution of an Order Form with Additional Terms. Contact your account representative for details. Also, Einstein
Engagement Scoring currently has no Admin level permission controls to limit users.
Einstein Engagement Scoring aggregates customer data in a dashboard that provides audience-level insights and individual contact-level
scores via a set of data extensions for MobilePush and Email.
Einstein Engagement Scoring populates the data extensions named Einstein_MC_Predictive_Scores and Einstein_MC_MobilePush_Scores.
Find engagement scoring data extensions via Contact Builder or Email Studio. Use these scores to:
• Monitor the health of your engaged subscriber list in a dashboard.
• Create an audience from scores using attributes similar to your best-performing subscribers.
• Segment your subscriber list to identify and target a specific audience based on their predicted likelihood to engage with your
campaigns.
• View model correlations that affect subscriber engagement using click bar graphs.
• Target subscribers through Marketing Cloud applications, such as Email Studio, Journey Builder, Marketing Cloud Advertising, or
Audience Builder.
• Use momentum analytics to gain insights about subscriber Persona changes and their relationship to subscriber categorization.

Note: Einstein Engagement Scoring uses Amazon Web Services. Einstein Engagement scores are refreshed weekly.
2

Prerequisites for Einstein Engagement Scoring

Up to 250 business units or MIDs per Enterprise ID can use Einstein Engagement Scoring for email. Einstein Engagement Scoring for
mobile is supported for customers that send email and use the Marketing Cloud Mobile SDK.
Activate Einstein Engagement Scoring
Turn on Einstein Engagement Scoring in Marketing Cloud Setup. Einstein requires historical contact or subscriber engagement data,
including at least 1,000 events in the 90 days before activation. It can take up to 90 days to generate initial scores, but engagement
scores are typically available 24–48 hours after implementation.
Einstein Engagement Scoring Dashboard
Use the dashboard to view engagement predictions for email and MobilePush channels, including the likelihood to click an email
or spend time in a mobile app, and other key performance indicators (KPI). To enable Web Conversion scoring, implement Collect
Tracking Code. You can analyze subscriber Persona changes over time.
Engagement Score Thresholds
Each key performance indicator (KPI) in Einstein Engagement Scoring has an Audience Health indicator. This indicator shows whether
the average grade for that score across all your subscribers is Excellent, Good, Fair, or Poor.

2
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

222
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

Einstein Engagement Scoring Personas

The Einstein Engagement Scoring heat map groups subscribers into a customer persona based on predicted email engagement.
Gauge Your Einstein Engagement Scoring Data Quality
Check your mobile app’s data quality score for insight about the engagement data that Einstein uses to predict your customers’
likelihood to engage. Data quality scores for Einstein Engagement Scoring are generated at the mobile app level only.
Create an Audience from Einstein Engagement Scores
Audience Builder offers pre-built Einstein Engagement Scoring dimensions to quickly and easily apply data science models to
personalize your marketing campaigns and customer journeys.
Einstein Engagement Scoring for Mobile Model Card
The model in this card analyzes each contact’s engagement record to assign scores for the contact’s likelihood to interact with mobile
messaging.
Einstein Engagement Scoring for Email Model Card
The model analyzed in this card predicts five types of engagement scores for each individual consumer contact in each customer’s
business unit. Predictions include email opens and clicks, subscriber retention, web conversion, and overall engagement.
Einstein Engagement Scoring FAQs
Get the answers to frequently asked questions about Einstein Engagement Scoring.

SEE ALSO:
Data Protection and Privacy

Prerequisites for Einstein Engagement Scoring

Up to 250 business units or MIDs per Enterprise ID can use Einstein Engagement Scoring for email. Einstein Engagement Scoring for
mobile is supported for customers that send email and use the Marketing Cloud Mobile SDK.

Considerations
• Einstein Engagement Scoring in Marketing Cloud analyzes only commercial send data, not transactional send data.
• Einstein Engagement Scoring uses automations in Marketing Cloud to collect, convert, and export email send tracking data to the
Einstein Platform. You can disable those automations, but this action can make engagement scores inaccurate when you re-enable
the automations.
• The Einstein Engagement Scoring Email Unsubscribe Prediction tile doesn’t work with custom unsubscribe handling, which can
result in inaccurate Subscriber Retention key performance indicator (KPI) modeling. Using the LogUnsubEvent API is a standard
unsubscribe, not custom.
• Einstein Engagement Scoring doesn’t support field-level encryption. SQL table data can’t be field-level encrypted.
• Einstein Engagement Scoring requires at least 14 days of active subscriber evaluation in each business unit before you can view
Persona changes over time.

Audience Builder Integration Considerations

These Audience Builder integrations each require a separate services engagement or support. Contact your Marketing Cloud account
representative for more information.
• Einstein Engagement Scoring provisioning for Audience Builder
• Activation with custom Audience Builder implementations

223
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

• Audience Builder implementations using Business Unit Filters

Web Conversion Modeling Considerations

• To use Web Conversion predictions, first set up a catalog and Collect Tracking Code for your website.
• Einstein Engagement Scoring supports subscriber key, which can be implemented with a support request. You can also use email
address, or MD5 Hashed lowercase version of email address as your subscriber identifier in Collect Tracking Code.
• You can’t import historical purchase data.
• Web Conversions require 90 days after Einstein Engagement Scoring activation to collect enough data to create a model.
• Web Conversions requires enablement. Contact your Marketing Cloud account representative for more information.
3

SEE ALSO:
Einstein Engagement Scoring
MobilePush SDK Setup Overview

Activate Einstein Engagement Scoring

Turn on Einstein Engagement Scoring in Marketing Cloud Setup. Einstein requires historical contact or subscriber engagement data,
including at least 1,000 events in the 90 days before activation. It can take up to 90 days to generate initial scores, but engagement
scores are typically available 24–48 hours after implementation.
Einstein Engagement Scoring currently has no admin level permission controls. Up to 250 business units or MIDs per Enterprise ID can
use Einstein Engagement Scoring for email.
Activate Einstein Engagement Scoring for mobile for each business unit, then choose mobile apps in the business unit to activate.
Activate scoring and customize scoring thresholds for as many mobile apps as you wish. Check Marketing Cloud Setup to make sure
each mobile app you activate is active and has sufficient data.

Note: Einstein Engagement Scoring is included with Corporate and Enterprise Edition, and is available as an add-on purchase to
Pro Edition. For customers that purchased a Corporate or Enterprise Edition before October 27, 2017, Einstein Engagement Scoring
is available at no additional charge upon execution of an Order Form with Additional Terms. Contact your account executive for
details.
1. Navigate to Marketing Cloud Setup.
2. Click Einstein.
3. Click Einstein Engagement Scoring.
4. Click Activate Einstein Engagement Scoring.
5. Click Email or Mobile.
a. For Email, click Activate.
b. For Mobile, click Get Started.
c. Select the mobile apps to activate Einstein Engagement Scoring for.
d. Click Activate.

3
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

224
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

After activation completes, edit engagement score thresholds by clicking , then Edit Thresholds. Select Use custom thresholds,
and save the updates you make.
4

Einstein Engagement Scoring for Email Data Extension

The Einstein_MC_Predictive_Scores data extension stores Einstein Engagement Scoring for email metrics. Scoring metrics are
updated weekly.
Einstein Engagement Scoring for MobilePush Data Extension
The Einstein_MC_MobilePush_Scores data extension stores Einstein Engagement Scoring for MobilePush metrics. Scoring metrics
are updated weekly.

SEE ALSO:
Marketing Cloud Advertising
Audience Builder
Journeys and Messages
Prerequisites for Einstein Engagement Scoring

Einstein Engagement Scoring for Email Data Extension

The Einstein_MC_Predictive_Scores data extension stores Einstein Engagement Scoring for email metrics. Scoring metrics are updated
weekly.

Warning: Don’t delete or modify the data extensions named Einstein_MC_Predictive_Scores and Einstein_MC_MobilePush_Scores.

Einstein_MC_Predictive_Scores Fields include:

• Email_Address (text, 256 characters)
• EmailClickLikelihood (text, 256 characters)
• EmailClickScore (decimal)
• EmailOpenLikelihood (text, 256 characters)
• EmailOpenScore (decimal)
• EmailSubscribeLikelihood (text, 256 characters)
• EmailSubscribeScore (decimal)
• EmailEngagementPersona (text, 256 characters)
• ConversionLikelihood (text, 256 characters)
• ConversionScore (decimal)
• UpdatedDate (date)
• CreatedDate (date)

Note: The EmailOpenScore and EmailClickScore can exceed the value 1.0.

To export the data, find the Einstein_MC_Predictive_Scores data extension in Email Studio or Contact Builder and click Export.

4
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

225
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

SEE ALSO:
Contact Builder in Marketing Cloud

Einstein Engagement Scoring for MobilePush Data Extension

The Einstein_MC_MobilePush_Scores data extension stores Einstein Engagement Scoring for MobilePush metrics. Scoring metrics are
updated weekly.

Warning: Don’t delete or modify the data extensions named Einstein_MC_Predictive_Scores and Einstein_MC_MobilePush_Scores.

Einstein_MC_MobilePush_Scores Fields include:

• SubscriberKey (255 character max string)
• AppID (255 character max string)
• DirectOpenScore (0-1)
• DirectOpenLevel (Most Likely, More Likely, Less Likely, Least Likely)
• InferredOpenScore (0-1)
• InferredOpenLevel (Most Likely, More Likely, Less Likely, Least Likely)
• PredictedSessionsScore (Integer)
• PredictedSessionsLevel (Most Engaged, More Engaged, Less Engaged, Least Engaged)
• PredictedTimeInApp (Time in Seconds)
• PredictedTimeInAppLevel (Most Engaged, More Engaged, Less Engaged, Least Engaged)
• EngagementScore (0-1)
• EngagementPersona (Most Engaged, More Engaged, Less Engaged, Least Engaged)
• UpdatedDate (date)
• CreatedDate (date)
To export the data, find the Einstein_MC_Predictive_Scores data extension in Email Studio or Contact Builder and click Export.

Note: The SubscriberKey field must be all lowercase.

6

SEE ALSO:
Contact Builder in Marketing Cloud

Einstein Engagement Scoring Dashboard

Use the dashboard to view engagement predictions for email and MobilePush channels, including the likelihood to click an email or
spend time in a mobile app, and other key performance indicators (KPI). To enable Web Conversion scoring, implement Collect Tracking
Code. You can analyze subscriber Persona changes over time.
To access the Einstein Engagement Scoring dashboard, go to Einstein and click Einstein Engagement Scoring. Then, click a tab to
choose the message channel dashboard to show. On the mobile dashboard, select an app to view predictions.

5
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.
6
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

226
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

Each engagement prediction tile displays:

• Activity Prediction: Average likelihood for each engagement metric over the next 7 days
• Change vs Last Week: Change in the average prediction week over week
• Audience Health Indicator: Assessment of audience health for each engagement metric benchmarked against email and mobile
industry standards
• Model Confidence Indicator: Relative predictive strength of your subscriber engagement scores
7

Einstein Engagement Scoring for Email Dashboard

On the email dashboard, get email engagement prediction data that groups contacts into a persona based on engagement thresholds.
Use detail pages to dig into prediction specifics and audience health.
Einstein Engagement Scoring for Mobile Dashboard
On the mobile dashboard, predicted app engagement groups contacts into four segments based on engagement thresholds.
Thresholds are shown beneath each segment.
Einstein Engagement Scoring Model Confidence
Model confidence is a way to express the relative strength of a prediction generated by a model. Understanding the concept can
help you interpret Einstein Engagement Scoring for email model confidence scores.

Einstein Engagement Scoring for Email Dashboard

On the email dashboard, get email engagement prediction data that groups contacts into a persona based on engagement thresholds.
Use detail pages to dig into prediction specifics and audience health.
The email engagement heat map groups subscribers into a customer persona based on predicted email engagement.
• Loyalists: Subscribers with high open and click engagement
• Window Shoppers: Subscribers with high open and low click engagement
• Selective Subscribers: Subscribers with low open and high click engagement
• Winback/Dormant: Subscribers with low open and click engagement

7
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

227
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

Note: Einstein Engagement Scoring still considers opens, but they’re weighted lower than clicks by Einstein’s AI models. Open
data is important to determine who, for example, is a window shopper versus a selective subscriber, or what differentiates a loyalist
from a selective subscriber. See Marketing Cloud Einstein Updates for Email Client Privacy Changes on page 210 for more information
about Einstein’s AI models regarding open-rate scoring.

Click the Time Comparison option to show subscriber Persona changes over time. Use this feature to analyze how your messaging is
resonating with your subscribers. For example, if your total number of subscribers increased by 10,000 since the last period, you can see
that your Loyalist bucket increased by 5,000 and that 70% of your new Loyalists are coming from your Selective Subscriber persona
bucket. Einstein Engagement Scoring requires at least 14 days of active subscriber evaluation in each business unit before you can view
Persona changes over time.

228
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

On the email dashboard, click View Details in a tile to view its engagement Key Performance Indicator (KPI) detail page. The engagement
KPI detail pages show:
• Activity Prediction: Average likelihood of each engagement metric during the next 7 days
• Audience Health Indicator: Audience health for each engagement metric benchmarked against email industry standards
• Activity Prediction Histogram: Distribution of subscribers based on likely engagement during the next 7 days
• Top Predictors: List of predictors used in the data learning model according to size of influence and positive or negative correlation

8
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

229
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

Einstein Engagement Scoring for Mobile Dashboard

On the mobile dashboard, predicted app engagement groups contacts into four segments based on engagement thresholds. Thresholds
are shown beneath each segment.
The mobile engagement heat map groups contacts into a customer persona based on predicted engagement.

Click the Time Comparison option to show Contact Persona changes over time. Use this feature to analyze how your messaging is
resonating with your contacts. For example, if your total number of contacts increased by 10,000 since the last period, you can see that
your Most Engaged bucket increased by 5,000 and that 70% of your new Most Engaged contacts are coming from your Less Engaged
persona bucket. Einstein Engagement Scoring requires at least 7 days of active contact evaluation in each business unit before you can
view Persona changes over time.

230
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

• Predicted App Engagement: This prediction is a blended metric that incorporates predicted app sessions, direct opens, inferred
open, and time in app to gauge engagement across message and application engagement. You can’t customize the weight of each
prediction in the score.
• Predicted App Sessions: How many sessions your audience is expected to generate on average.
• Predicted Direct Opens: How often your audience is expected to tap directly on a push notification to open an app on average
• Predicted Inferred Opens: How often your audience is expected to open the application within 24 hours of receiving, but not directly
opening a message. You can’t customize the 24-hour window, but opens that occur later in the window have less weight in the
prediction.
• Predicted Time in App: How much time in app your audience is expected to spend on average
9

9
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

231
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

Einstein Engagement Scoring Model Confidence

Model confidence is a way to express the relative strength of a prediction generated by a model. Understanding the concept can help
you interpret Einstein Engagement Scoring for email model confidence scores.
Model confidence provides the probability a random positive sample has a higher probability of being positive than a random negative
sample. Marketing Cloud uses the area under the Receiver Operating Characteristic curve or, auROC curve, analysis to evaluate the
strength of subscriber engagement predictions. Scores are smoothed so they present an even, understandable view of your customer
personas.
When model confidence is closer to 1.00, or 100%, there’s greater predictive strength for that engagement score. Lower model confidence
indicates weaker predictive strength for that engagement score. The closer the confidence is to 0.50, or 50%, the more the model has
about the same predictive strength of a coin toss. These are the model confidence thresholds for Einstein Engagement Scoring.
• Excellent: 1.00–0.85
• Good: 0.84–0.75
• Fair: 0.65–0.50
• Poor: < 0.50
Each engagement prediction tile on the dashboard contains a model confidence indicator. The indicator consists of three circles that
correspond with the model confidence thresholds:
• Excellent: three filled dots
• Good: two filled dots
• Fair: one filled dot
• Poor: no filled dots
Fair or poor model confidence can indicate insufficient subscriber data. It also can result from a change in email marketing strategy that
influences subscriber engagement behaviors.
10

SEE ALSO:
Einstein Engagement Scoring Dashboard
Engagement Score Thresholds

Engagement Score Thresholds

Each key performance indicator (KPI) in Einstein Engagement Scoring has an Audience Health indicator. This indicator shows whether
the average grade for that score across all your subscribers is Excellent, Good, Fair, or Poor.
The grades are equivalent to the likelihoods that are assigned to each subscriber:
• Excellent: Most Likely
• Good: More Likely
• Fair: Less Likely
• Poor: Least Likely
To make that determination, the Audience Health indicator uses score thresholds based on your threshold settings for Einstein Engagement
Scoring.
Email

10
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

232
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

• Local Averages (default)

• Global Averages (alternative default)
• Custom Thresholds
MobilePush
• App’s Averages (default)
• Global Averages (alternative default)
• Custom Thresholds
Default averages use your business unit’s email or, for MobilePush, the app’s own historical performance. It subjectively compares your
customers’ likely engagement.
For the alternative defaults, Salesforce trains each customer’s model using that customer’s behavioral data. If a customer opts in to the
Global Models feature, they can leverage a wider pool of probabilistic contact matching using a greater range of training data. Learn
more on page 219 about Marketing Cloud Einstein’s Global Models feature.

Note: Local and global averages replace the industry averages for engagement scoring for email thresholds. The new local and
global average default settings are optimized for the new blended scores that Marketing Cloud Einstein apps are leveraging.
11

SEE ALSO:
Activate Einstein Engagement Scoring
Einstein Engagement Scoring Dashboard
Einstein Engagement Scoring Model Confidence

Einstein Engagement Scoring Personas

The Einstein Engagement Scoring heat map groups subscribers into a customer persona based on predicted email engagement.
• Loyalists: Subscribers with high engagement scores.
• Window Shoppers and Selective Subscribers: Subscribers with mid-range engagement scores.
• Winback/Dormant: Subscribers with low engagement scores.
Use personas to refine customer engagement campaigns and journeys. Use the Time Comparison option in Predicted Email Engagement
on the Einstein Engagement Scoring Dashboard to show subscriber Persona predicted behavior changes over time.
Einstein Engagement Scoring still considers opens, but they’re weighted lower than clicks by Einstein’s AI models. Open data is important
to determine who, for example, is a window shopper versus a selective subscriber, or what differentiates a loyalist from a selective
subscriber. See Marketing Cloud Einstein Updates for Email Client Privacy Changes on page 210 for more information about Einstein’s
AI models regarding open-rate scoring.

Note: Some email client providers’ security updates can result in an email open without user engagement. See the Marketing
Cloud Einstein Updates for Email Client Privacy Changes on page 210 document for more information.
12

SEE ALSO:
Create an Audience from Einstein Engagement Scores

11
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.
12
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

233
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

Gauge Your Einstein Engagement Scoring Data Quality

Check your mobile app’s data quality score for insight about the engagement data that Einstein uses to predict your customers’ likelihood
to engage. Data quality scores for Einstein Engagement Scoring are generated at the mobile app level only.
Each mobile app’s data quality score is generated by analyzing the app’s engagement data. This analysis determines a Pattern Predictability
score and a Data Maturity score.
• To determine the Pattern Predictability score, Einstein analyzes the distinctness of your customers’ engagement patterns with your
mobile app. Greater pattern predictability leads to more accurate predictions of future engagement behavior. When your messages
are more compelling and drive higher engagement rates, your Pattern Predictability score is higher. When your engagement rates
are lower, your Pattern Predictability score is lower. Pattern Predictability differs from engagement rate because it evaluates engagement
events as they correlate to one another throughout your customers’ engagement history.
• To determine the Data Maturity score, Einstein analyzes the length of time that each of your customers has had data available to
make predictions, and how much data is available. This score helps Einstein understand how sensitive your subscribers are to changes
in your sending patterns over time. When you have a greater history of data for each of your customers, your Data Maturity score is
higher.
To find your data quality score, navigate to the Einstein Engagement Scoring for MobilePush dashboard. To see your scores and tips that
can help raise your data quality score, click Data Quality Score.

Note: Transactional sends and test sends are excluded when generating your data quality score.

SEE ALSO:
Einstein Engagement Scoring for Mobile Model Card
Evolve Your Marketing Strategy with Artificial Intelligence

Create an Audience from Einstein Engagement Scores

Audience Builder offers pre-built Einstein Engagement Scoring dimensions to quickly and easily apply data science models to personalize
your marketing campaigns and customer journeys.
13

1. Create an Audience
Create an audience from Einstein Engagement Scoring.
2. Configure Exclusion Criteria
Set exclusion criteria when you create an audience from Einstein Engagement Scoring.
3. Configure Audience Segment Criteria
To create an audience from Einstein Engagement Scoring, set the audience segment criteria.
4. Publish the Audience
Publish an audience that was created using Einstein Engagement Scoring. The audience is not available until it is published.

Create an Audience
Create an audience from Einstein Engagement Scoring.
1. Navigate to Audience Builder in the app switcher and select Audience Builder.

13
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

234
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

2. Click Create Audience.

3. Select Einstein Engagement Scoring in the attribute library.
4. Choose an email goal from the dropdown menu or drag it to the canvas to include the entire contact group.
5. If you want to refine your selection, drag the contact scores you want to include to the canvas area.
6. If you select more than one criteria, repeat steps 4 and 5, and select an operator.
7. Click Refresh.
The audience count field populates.
8. Save.
9. Name your audience, provide a description, and click Done.
10. Click Save.

Note: Don’t forget to publish the audience so it’s available.

14

Configure Exclusion Criteria

Set exclusion criteria when you create an audience from Einstein Engagement Scoring.
1. To exclude criteria, on the Exclusion tab click New Exclusion.
2. Name the exclusion.
3. Drag criteria to be excluded to the canvas.
To apply advanced exclusion options, complete the Advanced Options tab and click Done.

4. Click Refresh.

Note: You can add exclusion criteria to each filtered group within the audience.

15

Configure Audience Segment Criteria

To create an audience from Einstein Engagement Scoring, set the audience segment criteria.
1. To further segment your new audience, on the Segments tab click New Segment.
2. Enter a name for the segment.
3. Drag the segment criteria to the canvas.
To apply advanced segmentation options, complete the Advanced Options tab and click Done.

4. Click Refresh.
You can segment each filtered group within your audience.
16

14
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.
15
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.
16
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

235
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

Publish the Audience

Publish an audience that was created using Einstein Engagement Scoring. The audience is not available until it is published.
1. Click the Publish tab.
2. Complete the fields under audience type.
3. Select attributes you want to append.
4. To view results, click Publish Preview.
5. If needed, change your selections in steps 2 and 3.

Tip: Delete selections from your canvas by clicking the trashcan icon.

6. Click Save and Publish.

7. Click Save and Exit.
17

Einstein Engagement Scoring for Mobile Model Card

The model in this card analyzes each contact’s engagement record to assign scores for the contact’s likelihood to interact with mobile
messaging.
18

Model Details
The Marketing Cloud Einstein Engagement Scoring for Mobile model predicts engagement using training algorithms, parameters,
fairness constraints, features, and other applied approaches.
Intended Use
The Marketing Cloud Einstein Engagement Scoring for Mobile model is intended for these use cases.
Relevant Factors
These factors are associated with the Marketing Cloud Einstein Engagement Scoring for Mobile model.
Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance
measures are associated with the Marketing Cloud Einstein Engagement Scoring for Mobile model.
Training Data
You have a customized version of the model that’s trained on your data alone, unless you’re opted in to use global model data. Data
from one Salesforce customer doesn’t affect the behavior for another Salesforce customer. While model training happens for each
customer on their data, the initial development of the model is validated with a representative set of pilot customers’ data.
Ethical Considerations
Review ethical factors associated with the Marketing Cloud Einstein Engagement Scoring for Mobile model. To avoid bias and other
ethical risks, the Einstein Content Selection and Testing model doesn’t include demographic data.
Einstein Engagement Scoring for Mobile Model Refresh
Understand the refresh cadence associated with the Marketing Cloud Einstein Email Engagement Scoring model.

17
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.
18
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

236
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

Model Details
The Marketing Cloud Einstein Engagement Scoring for Mobile model predicts engagement using training algorithms, parameters, fairness
constraints, features, and other applied approaches.

Person or Organization
Salesforce Marketing Cloud Einstein

Model Date and Version

• August 2020
• Minor changes can occur throughout the release
• Major changes can occur and are communicated via release notes

Model Type
Forecasting, Time-series analysis, Clustering

General Information
• Einstein Engagement Scoring for Mobile predicts five types of engagement scores for each individual mobile consumer contact
within each customer’s apps.
– Likelihood to tap on a push notification
– Likelihood of an inferred open
– Predicted spending time in app over the next 7 days
– Predicted app sessions over the next 7 days
– Predicted overall, aggregated app engagement

• Push direct open cards show the likelihood of your engaged contacts to open an app directly from a push notification. The trend
shows the change in average likelihood for the past 7 days.
• Push indirect open cards show the likelihood of your engaged contacts to open an app after receiving a push notification without
tapping the app from the push notification. The trend shows the change in average likelihood for the past 7 days.
• The model further classifies each score into one of four categories based on customer-defined thresholds or machine-inferred
thresholds.
• The model analyzes an individual contact’s historical events and engagement patterns to forecast future engagement scores. More
recent behavior and engagement patterns are emphasized more heavily in the predictions.
• The model clusters predicted engagement scores to derive local threshold boundaries to classify contact engagement levels.
• Salesforce trains each customer’s model using only that customer’s app data. If a customer opts in to the Global Models feature, they
can leverage a wider pool of probabilistic contact matching using a greater range of training data.

Tip: Learn more on page 219 about Marketing Cloud Einstein’s Global Models feature.

Constraints
• A minimum of 1 push or open event is required for a contact to have prediction scores.

237
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

License
Mobile Engagement Scoring is available to use for Salesforce Marketing Cloud customers with any of these editions.
• Corporate Edition
• Enterprise Edition
• Enterprise+ Edition

Questions or Comments
Send questions or comments about the model to mce-support@salesforce.com.

Intended Use
The Marketing Cloud Einstein Engagement Scoring for Mobile model is intended for these use cases.

Primary Intended Uses

The Einstein Mobile Engagement Scoring model offers five types of application specific predicted engagement likelihood for each mobile
subscriber, for marketing professionals to have a deeper understanding of their subscribers, so that they can conduct further segmentation
or better targeting on future mobile campaigns and sends.

Out-of-Scope Use Cases

Anything other than the primary use case is out of scope and is not recommended.

Relevant Factors
These factors are associated with the Marketing Cloud Einstein Engagement Scoring for Mobile model.

Model Input
Einstein Engagement Scoring for Mobile analyzes up to 90 days of historical engagement patterns of the subscribers. The engagement
history includes these factors.
• Push events and reactions, such as push notifications and taps on push notifications, and associated timestamps
• App engagement behavior, such as app opens and time spent in app, and associated timestamps
• Data and metadata about customer sending patterns, including how campaigns are executed
• Categorization thresholds defined by customers when applicable
The engagement history that Einstein Engagement Scoring for Mobile analyzes excludes these factors.
• Data purchased or collected from third parties
• Demographic data that is typically stored in SFMC as data extensions or subscriber or contact attributes
• Specific content within the push notification template or rendered message body

Model Output
• Up to five types of scores are predicted for each subscriber for each business unit.
• For each business unit, the model produces an average score across all subscribers and associated model confidence level.
• The model produces data extensions that contain each subscriber’s predicted scores and the corresponding category.

238
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

• The model recommends local thresholds based on your data for each score type.

Groups
The model doesn’t include demographic data or other data purchased from third-party data providers.

Environment
The model is trained and deployed in the Salesforce Marketing Cloud environment.

Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance measures
are associated with the Marketing Cloud Einstein Engagement Scoring for Mobile model.

Model Performance Measures

Model performance metrics include metrics like model fitness score (root mean squared error, mean absolute error) and data richness
score.

Training Data
You have a customized version of the model that’s trained on your data alone, unless you’re opted in to use global model data. Data
from one Salesforce customer doesn’t affect the behavior for another Salesforce customer. While model training happens for each
customer on their data, the initial development of the model is validated with a representative set of pilot customers’ data.

Ethical Considerations
Review ethical factors associated with the Marketing Cloud Einstein Engagement Scoring for Mobile model. To avoid bias and other
ethical risks, the Einstein Content Selection and Testing model doesn’t include demographic data.
Salesforce customers are responsible for their interpretation of results generated by the model. Customers must be aware of any
assumptions they make when acting based on scores generated by the model. There are potential adverse outcomes in certain
circumstances. For example, if the model predicts low engagement, a marketer can simply choose not to send a marketing communication.
If that prediction were erroneous, there can be negative impact in the exclusion of certain audiences or individuals from access to benefits
or opportunities.

Example: The Einstein Engagement Scoring for Mobile model predicts low engagement within a marketer’s target audience.
The marketer chooses not to send their marketing communication based on this prediction. If that prediction is erroneous, some
audiences or individuals are excluded from access to benefits or opportunities.

Einstein Engagement Scoring for Mobile Model Refresh

Understand the refresh cadence associated with the Marketing Cloud Einstein Email Engagement Scoring model.

Scores and Models

Einstein Engagement Scoring scores and models for email are updated approximately weekly. The refresh cadence varies by one to
several days based on a customer's individual business unit.

239
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

Einstein Engagement Scoring for Email Model Card

The model analyzed in this card predicts five types of engagement scores for each individual consumer contact in each customer’s
business unit. Predictions include email opens and clicks, subscriber retention, web conversion, and overall engagement.

Model Details
The Marketing Cloud Einstein Engagement Scoring model predicts customer engagement with email content using these training
algorithms, parameters, fairness constraints, and features.
Intended Use
The Marketing Cloud Einstein Engagement Scoring model is intended for these use cases.
Relevant Factors
These factors are associated with the Marketing Cloud Einstein Engagement Scoring model.
Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance
measures are associated with the Marketing Cloud Einstein Engagement Scoring model.
Training Data
You have a customized version of the model that’s trained on your data alone, unless you’re opted in to use global model data. Data
from one Salesforce customer doesn’t affect the behavior for another Salesforce customer. While model training happens for each
customer on their data, the initial development of the model is validated with a representative set of pilot customers’ data.
Ethical Considerations
Review the ethical factors associated with the Marketing Cloud Einstein Email Engagement Scoring model. To avoid bias and other
ethical risks, the Einstein Email Engagement Scoring model doesn’t include demographic data.
Refresh Cadence
Review the refresh cadence associated with the Marketing Cloud Einstein Email Engagement Scoring model.

Model Details
The Marketing Cloud Einstein Engagement Scoring model predicts customer engagement with email content using these training
algorithms, parameters, fairness constraints, and features.

Person or Organization
Salesforce Marketing Cloud Einstein

Model Date and Version

• October 2021
• Minor changes can occur throughout the release
• Major changes can occur and are communicated via release notes

Model Type
Forecasting, Time-series analysis. Classification, Clustering

240
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

General Information
Einstein Email Engagement Scoring predicts five types of engagement scores for each individual consumer contact in each customer’s
business unit. The model further classifies each score into one of four categories based on customer-defined thresholds or machine-inferred
thresholds. The model analyzes an individual subscriber’s historical events and engagement patterns to forecast future engagement
scores. The most recent behavior and engagement patterns are emphasized in the predictions. The web conversion model is a classification
model with crafted features based on historical web interaction events. The model clusters predicted engagement scores to derive local
threshold boundaries to classify contact engagement levels.

Constraints
A minimum of one email send is required for a contact to have prediction scores.

License
Einstein Email Engagement Scoring is available to Salesforce Marketing Cloud customers with any of these editions.
• Corporate Edition
• Enterprise Edition
• Enterprise+ Edition

Questions or Comments
Send questions or comments about the model to mce-support@salesforce.com.

Intended Use
The Marketing Cloud Einstein Engagement Scoring model is intended for these use cases.

Primary Intended Uses

The Einstein Email Engagement Scoring model offers five types of application-specific engagement likelihood for each subscriber. This
insight gives you a deeper understanding of your subscribers so you can segment further and target better in future campaigns and
sends.

Out-of-Scope Use Cases

Anything other than the primary use case is out of scope and not recommended.

Relevant Factors
These factors are associated with the Marketing Cloud Einstein Engagement Scoring model.

Model Input
Einstein Email Engagement Scoring analyzes up to 90 days of historical engagement patterns of the subscribers. The engagement history
includes these factors.
• Email sends, bounces, and engagement events including open, click, and unsubscribe, and associated timestamps
• User retention and subscription history
• Subscriber web interaction events including view, search, profile, and purchase, with associated timestamps

241
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

• Data and metadata about customer sending patterns, including how campaigns are executed
• Categorization thresholds defined by customers when applicable
The engagement history that Einstein Engagement Scoring for Mobile analyzes excludes these factors.
• Data purchased or collected from third parties
• Demographic data that is typically stored in SFMC as data extensions or subscriber or contact attributes
• Specific content within the email template or rendered email body

Model Output
• Up to five score types are predicted for each subscriber for each business unit.
• For each score type, the model produces a list of important factors with impact levels.
• For each business unit, the model produces an average score across all subscribers and an associated model confidence level.
• The model produces data extensions that contain each subscriber’s predicted scores and the corresponding category.
• The model recommends a threshold based on your data that you can use to classify different engagement levels for each score type.

Groups
The model doesn’t use demographic data or other data purchased from third-party data providers.

Environment
The model is trained and deployed in the Salesforce Marketing Cloud environment.

Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance measures
are associated with the Marketing Cloud Einstein Engagement Scoring model.

Model Performance Measures

Model performance metrics include data such as the model fitness score based on the root mean squared error and mean absolute
error, and the data richness score.

Training Data
You have a customized version of the model that’s trained on your data alone, unless you’re opted in to use global model data. Data
from one Salesforce customer doesn’t affect the behavior for another Salesforce customer. While model training happens for each
customer on their data, the initial development of the model is validated with a representative set of pilot customers’ data.

Ethical Considerations
Review the ethical factors associated with the Marketing Cloud Einstein Email Engagement Scoring model. To avoid bias and other
ethical risks, the Einstein Email Engagement Scoring model doesn’t include demographic data.
Customers are responsible for interpreting Einstein’s insights, and they must be aware of any assumptions that they make when acting
based on the model’s insights. However, adverse outcomes are possible due to model error. For example, a marketer chooses not to
send a marketing communication based on a model incorrectly predicting low engagement. As a result, certain audiences and individuals
miss access to benefits and opportunities.

242
Marketing Cloud Einstein and Analytics Einstein Engagement Scoring

Refresh Cadence
Review the refresh cadence associated with the Marketing Cloud Einstein Email Engagement Scoring model.

Scores and Models

Einstein Engagement Scoring scores and models for email are updated weekly. The refresh cadence varies by one to several days based
on a customer's individual business unit.

Einstein Engagement Scoring FAQs

Get the answers to frequently asked questions about Einstein Engagement Scoring.
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

Why isn’t Einstein Engagement Scoring automatically enabled in my account?

Not every Marketing Cloud account is used to market to subscribers via the email or web. For example, some are test accounts, some
are used for automations and some are used for other channels, such as social or mobile. This step ensures that we are scoring the
right audiences in an efficient, scalable manner.
Can I limit who has access to Einstein Engagement Scoring?
No, you cannot restrict Einstein Engagement Scoring permissions based on user roles.
Can I Customize the Prediction Model or Algorithm?
No, you cannot customize the models. Scores are smoothed so they present an even, understandable view of your customer personas.
The models are automatically tuned on the Einstein Platform.
Can I change the scheduled time for the automations to start?
Yes, however doing so could delay import of updated scores into your account and delay their availability in Audience Builder.
I see an engagement tile for web conversion, but the tile in the app says that this feature isn't enabled. Why?
Web Conversion is enabled for customers who have provisioned Einstein Web Recommendations and have set up the Collect
Tracking Code on their websites. If this product is not enabled in your account, contact your account executive for details.

Why isn’t Einstein Engagement Scoring automatically enabled in my account?

Not every Marketing Cloud account is used to market to subscribers via the email or web. For example, some are test accounts, some
are used for automations and some are used for other channels, such as social or mobile. This step ensures that we are scoring the right
audiences in an efficient, scalable manner.

Can I limit who has access to Einstein Engagement Scoring?

No, you cannot restrict Einstein Engagement Scoring permissions based on user roles.

Can I Customize the Prediction Model or Algorithm?

No, you cannot customize the models. Scores are smoothed so they present an even, understandable view of your customer personas.
The models are automatically tuned on the Einstein Platform.

Can I change the scheduled time for the automations to start?

Yes, however doing so could delay import of updated scores into your account and delay their availability in Audience Builder.

243
Marketing Cloud Einstein and Analytics Einstein Messaging Insights

To change an automation, see Schedule an Automation.

I see an engagement tile for web conversion, but the tile in the app says that this feature isn't
enabled. Why?
Web Conversion is enabled for customers who have provisioned Einstein Web Recommendations and have set up the Collect Tracking
Code on their websites. If this product is not enabled in your account, contact your account executive for details.

Einstein Messaging Insights

Einstein Messaging Insights alerts you to changes in your marketing performance no matter where you are in the Marketing Cloud. The
Einstein notifications badge appears in the header, where it’s constantly accessible to let you know how your email sends and journeys
perform. When an anomaly occurs, the notifications badge alerts you. Navigate to the insights hub for more information about quantifying
your results.
Einstein monitors the engagement rates (opens, clicks, and unsubscribes) of your email sends, including batch sends and journey sends.
When Einstein Messaging Insights finds an anomalously high or low result compared to the expected values, it generates an insight.
The insight denotes the anomaly and its context.

Example: A marketer at Northern Trail Outfitters created a journey that sends a weekly deals email to customers each Monday.
The marketer logs in to the Marketing Cloud after a long holiday weekend, and the Einstein notifications badge shows that insights
are waiting. The marketer clicks the badge and insights like the following appear.
High Engagement Rate for Journey “Weekly Deals Email”
18.25% higher than expected
The marketer then clicks the insight to find out more about it.
Now the marketer is aware of over- or under-performing emails, and for batch email sends can understand some of the key
underlying factors. Marketers can then calibrate their journeys or sends to make sure that they perform at their peak.
19

Set Up Einstein Messaging Insights

Einstein Messaging Insights is off by default for all units in an enterprise. To enable Einstein Messaging Insights, enter your MID, and
then choose the On button. Insights that relate to sends or journeys within a business unit are visible to all users in the business unit.
To allow analysis, an automation is created that moves data to the Marketing Cloud’s Einstein Platform.
View Einstein Messaging Insights
Check out recent insights by clicking the Einstein notifications badge that appears in the header. Or navigate to the insights hub to
review insights and quantify your email send and journey results with more information.
The Einstein Messaging Insights Dashboard
See more insights in one place and find out more about each insight on the Einstein Messaging Insights dashboard. Click an insight
to access contributing factors that influenced the send’s performance.
Einstein Messaging Insights Model Card
The model in this card analyzes message engagement rates and notifies marketers when anomalies in their marketing performance
occur.

19
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

244
Marketing Cloud Einstein and Analytics Einstein Messaging Insights

Set Up Einstein Messaging Insights

Einstein Messaging Insights is off by default for all units in an enterprise. To enable Einstein Messaging Insights, enter your MID, and then
choose the On button. Insights that relate to sends or journeys within a business unit are visible to all users in the business unit. To allow
analysis, an automation is created that moves data to the Marketing Cloud’s Einstein Platform.
1. Navigate to Marketing Cloud Setup.
2. Click Einstein.
3. Click Einstein Messaging Insights.
4. Activate Einstein Messaging Insights for your business unit.

Tip: Keep Messaging Insights off for business units that are used as sandboxes or contain only test data.

View Einstein Messaging Insights

Check out recent insights by clicking the Einstein notifications badge that appears in the header. Or navigate to the insights hub to
review insights and quantify your email send and journey results with more information.
1. After logging in to the Marketing Cloud, click the Einstein notifications badge in the header.
a. To see more insights and contextual information, click View All Insights.

2. To view insights and context directly, navigate to Einstein.

3. Click Einstein Messaging Insights.

The Einstein Messaging Insights Dashboard

See more insights in one place and find out more about each insight on the Einstein Messaging Insights dashboard. Click an insight to
access contributing factors that influenced the send’s performance.
Use the Einstein Messaging Insights dashboard to view and analyze anomalous results after a batch send or journey send. The dashboard
shows send-related information, such as Job ID, Date Sent, and Total Delivered. It also clearly shows data about each send and the
variable that was identified as an anomaly. Batch sends include factors that Einstein determines can influence send results. Contributing
factors appear in sentence format and table format.
• Einstein evaluates each journey and each send once each day to produce insights.
• Emails track events, such as opens and clicks, for many days after sending. Einstein uses the events collected for up to 7 days after
an email send to reassess whether the send is an anomaly or not.
• The variables that Einstein Messaging Insights measures for Journey Insights and Batch Send Insights are open rate, click rate, and
unsubscribe rate.

Journey Insights
• Rather than analyzing a single journey email against that email’s previous performance, Einstein analyzes all email activities in a
journey to find anomalies.
• Einstein uses up to 90 days of performance data to measure the rolling average performance of a variable. This average is used as
the expected value for the variable that’s measured.
• The upper bound on the dashboard is the anticipated maximum performance that Einstein calculates for the variable that’s measured.
The upper bound is set at a 95% confidence interval above the rolling average.

245
Marketing Cloud Einstein and Analytics Einstein Messaging Insights

• The lower bound is the anticipated minimum performance of the variable. The lower bound is set at a 95% confidence interval below
this rolling average.
• Journey updates such as activating a new version are indicated by dots on the graph. To find out what kind of update each dot
indicates, use the key beside the anomaly graph.
• Top Contributing Factors aren’t available for Journey Insights.

Batch Send Insights

• Einstein uses a group of similar sends from within the last 90 days to calculate the average performance of a variable. And Einstein
determines the similarity of sends using variables including send size and several other factors.
• The upper bound on the Einstein Messaging Insights dashboard is the anticipated maximum performance that Einstein calculates
for the variable that’s measured. The upper bound is set at 95% confidence interval above the average performance of the variable
for a send of this size.
• The lower bound is the anticipated minimum performance of the variable. The lower bound is set at a 95% confidence interval below
the average performance of the variable for a send of this size.
• When multiple insights are found for a single journey or batch send, a number appears next to the insight’s title. To view each insight,
click the insight’s title.

Einstein Messaging Insights Model Card

The model in this card analyzes message engagement rates and notifies marketers when anomalies in their marketing performance
occur.

1. Model Details
The Marketing Cloud Einstein Messaging Insights model provides insight about ongoing marketing email campaigns with email
content using these training algorithms, parameters, fairness constraints, and features.
2. Intended Use
The Marketing Cloud Einstein Messaging Insights model is intended for these use cases.
3. Relevant Factors
These factors are associated with the Marketing Cloud Einstein Messaging Insights model.
4. Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance
measures are associated with the Marketing Cloud Einstein Messaging Insights model.
5. Training Data
You have a customized version of the model that’s trained on your data alone. Data from one Salesforce customer doesn’t affect the
behavior for another Salesforce customer. While model training happens for each customer on their data, the initial development
of the model is validated with a representative set of pilot customers’ data.
6. Ethical Considerations
Review the ethical factors associated with the Marketing Cloud Einstein Messaging Insights model. To avoid bias and other ethical
risks, the Einstein Messaging Insights model doesn’t include demographic data. Customers are responsible for interpreting Einstein’s
insights, and must be aware of any assumptions that they make when acting based on the model’s insights.

246
Marketing Cloud Einstein and Analytics Einstein Messaging Insights

Model Details
The Marketing Cloud Einstein Messaging Insights model provides insight about ongoing marketing email campaigns with email content
using these training algorithms, parameters, fairness constraints, and features.

Person or Organization
Salesforce Marketing Cloud Einstein

Model Date and Version

• May 2020
• Minor changes can occur throughout the release
• Major changes can occur and are communicated via release notes

Model Type
Regression, Causation analysis, Time-series analysis

General Information
Einstein Messaging Insights is an anomaly detection system that surfaces noteworthy facts about ongoing marketing email campaigns
running in Marketing Cloud. The model can detect and compare campaigns with similar attributes, performance changes over time,
and relationship changes between activities for complex orchestration. The model comprises multiple decision tree regression models,
time series-based predictions, and graph analytics. Einstein trains each customer’s model only using that customer’s data.

Constraints
• A minimum of 10 email batches is required to model for batch insights.
• A minimum of 7 days of history is required to model for journey, journey activity, and frequent automation insights.

License
Einstein Messaging Insights is available to Salesforce Marketing Cloud customers with any of these editions.
• Corporate Edition
• Enterprise Edition
• Enterprise+ Edition

Questions or Comments
Send questions or comments about the model to mce-support@salesforce.com.

Intended Use
The Marketing Cloud Einstein Messaging Insights model is intended for these use cases.

247
Marketing Cloud Einstein and Analytics Einstein Messaging Insights

Primary Intended Uses

The Einstein Messaging Insights model powers Einstein notifications and the Einstein Messaging Insights dashboard hub. These tools
are designed for marketing professionals to see anomalously high or low engagement rates of email sends compared to expected values.
The feature notifies marketers of anomalies so that they can further investigate their journeys and email sends.

Out-of-Scope Use Cases

Anything other than the primary use case is out of scope and not recommended. For example, when an anomaly is raised, inferring that
related metrics like click-to-open rate (CTOR) are also anomalous isn’t an intended use case.

Relevant Factors
These factors are associated with the Marketing Cloud Einstein Messaging Insights model.

Model Input
Einstein Messaging Insights analyzes up to 90 days of historical engagement patterns of the Enterprise subscribers. The engagement
history includes these factors.
• Email sends, bounces, and engagement events including open, click, and unsubscribe, spam complaints, and associated timestamps
• Data and metadata about customer sending patterns, including how campaigns are executed. This data includes batch sends,
Journey Builder sends, and Automation Studio sends, transactional sends, and triggered sends
• Data and metadata about customer sending patterns, including past and future automations running in Automation Studio
• Pre-personalization subject lines are analyzed with unresolved AMPscript
• Email domain
The engagement history that Einstein Messaging Insights analyzes excludes these factors.
• Data purchased or collected from third parties
• Demographic Data, which is typically stored in SFMC as data extensions or subscriber or contact attributes
• Specific content within the email template or rendered email body

Model Output
The Einstein Messaging Insights model outputs these insights for three types of engagement (clicks, opens, and unsubscribes) daily.
Each insight is generated based on observed engagement rate and incorporates upper and lower confidence bounds. All insights include
anomaly degree, which measures severity of the insight’s impact.
• Batch insights, which consider anomalous batches sent over the past 7 days.
• Batch insights include top contributing signals with corresponding signal strengths.
• Journey insights, which consider anomalous journeys whose engagement rate is outside of the expected range.
• Journey activity insights, which consider anomalous journeys whose activities’ engagement rate’s overall change is outside of the
expected range.
• Automation insights, which consider anomalous frequent automations whose engagement rate is outside of the expected range.

Groups
The model doesn’t include any demographic data or other data purchased from third-party data providers. The model uses engagement
data such as opens, sends, and patterns.

248
Marketing Cloud Einstein and Analytics Einstein Send Time Optimization

Environment
The model is trained and deployed in the Salesforce Marketing Cloud environment.

SEE ALSO:
Infrastructure and Sub-processors for the Salesforce Marketing Cloud Services

Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance measures
are associated with the Marketing Cloud Einstein Messaging Insights model.

Model Performance Measures

We evaluate and monitor model performance metrics to ensure and improve the quality of the model. Model performance metrics
include metrics like model fitness score (root mean squared error) and confidence-bound tightness.

Training Data
You have a customized version of the model that’s trained on your data alone. Data from one Salesforce customer doesn’t affect the
behavior for another Salesforce customer. While model training happens for each customer on their data, the initial development of the
model is validated with a representative set of pilot customers’ data.

SEE ALSO:
Model Details

Ethical Considerations
Review the ethical factors associated with the Marketing Cloud Einstein Messaging Insights model. To avoid bias and other ethical risks,
the Einstein Messaging Insights model doesn’t include demographic data. Customers are responsible for interpreting Einstein’s insights,
and must be aware of any assumptions that they make when acting based on the model’s insights.

Einstein Send Time Optimization

Marketing Cloud Einstein Send Time Optimization (STO) determines the best time to send a message. Using machine learning, Einstein
predicts optimal send times so that a user is likely to engage with your message.
Einstein Send Time Optimization helps marketers increase email and push notification engagement. Using automated analysis, Einstein
determines the best time to send a message to each individual contact. Each week, Einstein uses each contact’s latest engagement data
for sends with the Commercial send classification to recreate its sending model with that data. Email sends with the Transactional send
classification aren’t used for modeling.
The Einstein STO Journey Builder activity sends messages to each contact at the time when that contact is most likely to engage with
the message. When Einstein doesn’t have enough data to create a model for a contact, the contact receives messages according to a
generalized model. The generalized model is derived from sending data in your Enterprise. The Einstein Send Time Optimization dashboard
displays analytics that predict future message engagement.
You can use Einstein STO in Automation Studio in a Send Email activity. Einstein gathers data for about 20 factors. It uses machine learning
and 90 days of engagement data to determine the best time within the next 24 hours to send an email message to each contact.
To use this activity, activate Einstein Send Time Optimization for your business unit.

249
Marketing Cloud Einstein and Analytics Einstein Send Time Optimization

Note: Einstein Send Time Optimization is included with Corporate and Enterprise Edition or available as an add-on purchase to
Pro Edition. Einstein Send Time Optimization is also available as an add-on to customers with Pro Edition who have Journey Builder.
For customers who have purchased a Corporate or Enterprise Edition before 10/27/2017, Einstein Send Time Optimization is
available at no additional charge upon execution of an Order Form with Additional Terms. Contact your account representative
for details.
20

Activate Einstein Send Time Optimization

Turn on Einstein Send Time Optimization (STO) in Marketing Cloud Setup to find out how sending works for subscribers with low
data.
Preview Einstein’s Optimal Send Times
Find out when Einstein would send for contacts in any data extension. Select any data extension, set the sending window, and get
a preview of optimal send times that Einstein identifies for your contacts. When a data extension has numerous rows, previews are
based on sampling data.
Einstein Send Time Optimization Dashboard
Visualize optimal predicted send times by the day or hour for all email addresses or contacts in a Marketing Cloud tenant or for all
contacts in a business unit. Find out when subscribers are most likely to engage with your messages, when Einstein recommends
sending, and insight about your Enterprise’s data quality, which fuels Einstein’s predictions.
Gauge Your Einstein Send Time Optimization Data Quality
Check your Enterprise’s data quality score for insight about the engagement data that Einstein uses to predict optimal send times.
Data quality scores for Einstein Send Time Optimization are generated at the Enterprise level only.
Einstein Send Time Optimization for Email Model Card
The model in this card analyzes the optimal time to send an email to a subscriber to maximize the probability of the subscriber
opening the email.
Einstein Send Time Optimization for Mobile Model Card
The model in this card analyzes the optimal time to send a mobile message to maximize a contact’s probability of interacting with
it. Einstein Send Time Optimization for Mobile is the Salesforce Marketing Cloud solution to optimize notification push time in order
to maximize the overall engagement of mobile apps.

SEE ALSO:
Activate Einstein Send Time Optimization

Activate Einstein Send Time Optimization

Turn on Einstein Send Time Optimization (STO) in Marketing Cloud Setup to find out how sending works for subscribers with low data.
This feature is available to customers with Marketing Cloud Einstein terms for Corporate, Enterprise, or Professional Edition accounts
with the Journey Builder add-on. To use this activity, activate Einstein Send Time Optimization for your business unit. In Setup, click Send
Time Optimization. On the Email tab, click Activate. Allow up to 72 hours after activation to complete the data transfer and analysis
required to optimize sends through Journey Builder or Automation Studio.
Insufficient Data Option

20
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

250
Marketing Cloud Einstein and Analytics Einstein Send Time Optimization

Einstein can only predict an optimal send time when there’s sufficient engagement data about a contact. When there isn’t enough data,
it’s because a contact is new or hasn’t engaged. So, STO sends messages according to a general model it creates for sending within your
Enterprise.

Tip: Except in special circumstances, use this option’s default Enterprise setting.

Complete these steps for each business unit where you plan to use the feature. You need at least one push notification app before you
turn on STO for push notification.
1. In the Marketing Cloud Setup app, expand Einstein, and click Send Time Optimization.
2. To choose a message channel, click a tab.
3. Click Activate.
4. Select the send time that the Einstein STO activity uses when there isn’t enough information about a subscriber to determine the
optimal send time.
5. Click Update.
6. Click Settings.
7. Select the time zone that STO presents results in.

Example: For example, you’re part of a small B2B business unit in an Enterprise that also has a large B2C business unit. The larger
B2C business unit’s contacts have different optimal send times than B2B customers. The B2C business unit has thousands of
contacts. So analyzing all contacts in the Enterprise could potentially skew the Enterprise-level model heavily towards times that
are unsuitable for the B2B business unit’s contacts. As a solution, the B2B business unit uses the Insufficient Data Option. This
option decouples their send times from the personalized send times that the B2C business unit uses.

Preview Einstein’s Optimal Send Times

Find out when Einstein would send for contacts in any data extension. Select any data extension, set the sending window, and get a
preview of optimal send times that Einstein identifies for your contacts. When a data extension has numerous rows, previews are based
on sampling data.
After you build a preview, it takes time to build before you see its results. In most cases, a data extension preview is built within a few
minutes. Check the progress indicator next to your preview to estimate how long it takes to build the preview.
When the data extension that a preview is based on is deleted, the preview is removed from the list after 90 days.
1. Select Einstein in the Marketing Cloud top navigation.
2. Click Einstein Overview
3. Click Preview.
4. Select a data extension.
5. Set a sending time frame.
6. Click Done.
Building the preview starts. You can navigate away while the build is in progress, then return to see results.
7. When the progress indicator reads Complete, click the preview to see a graph showing the optimal sending hours that Einstein
identifies for this data extension’s contacts.

Refresh a Send Time Preview

After you create a preview of a data extension, you can refresh it to find out if Einstein’s optimal send times have changed.

251
Marketing Cloud Einstein and Analytics Einstein Send Time Optimization

Delete a Send Time Preview

When a preview is no longer useful, you can delete it.

SEE ALSO:
Einstein Send Time Optimization for Journey Builder

Refresh a Send Time Preview

After you create a preview of a data extension, you can refresh it to find out if Einstein’s optimal send times have changed.
If you build a preview while a different preview is building or refreshing, the refresh process stops. When you delete the data extension
that a preview is based on, you can’t refresh the preview.
1. Select Einstein in the Marketing Cloud top navigation.
2. Click Einstein Overview
3. Click Preview.
4. Click a completed preview to refresh.
5. Click Refresh.
Building the preview starts. You can navigate away while the build is in progress, then return to see results.
6. When the progress indicator reads Complete, click the preview to see a graph showing the optimal sending hours that Einstein
identifies for this data extension’s contacts.

Delete a Send Time Preview

When a preview is no longer useful, you can delete it.
When the data extension that a preview is based on is deleted, the preview is removed from the list after 90 days.
1. Select Einstein in the Marketing Cloud top navigation.
2. Click Einstein Overview
3. Click Preview.
4. Click a preview to delete.
5. Click Delete.
6. Confirm that you want to delete the preview.

Einstein Send Time Optimization Dashboard

Visualize optimal predicted send times by the day or hour for all email addresses or contacts in a Marketing Cloud tenant or for all contacts
in a business unit. Find out when subscribers are most likely to engage with your messages, when Einstein recommends sending, and
insight about your Enterprise’s data quality, which fuels Einstein’s predictions.
To access the Einstein Send Time Optimization (STO) dashboard, go to Einstein in the nav menu, and click Einstein Send Time
Optimization. Then click a tab to choose the message channel dashboard to show.
Use the Einstein Send Time Optimization dashboard to view optimal send times by day or by hour. Optimal send times are based on
how many contacts are predicted to engage with the message you send. Or view optimal send times across the days and hours in a
week. Knowing the optimal send time by hour or day can help you choose the best time for batch sends.
• Total Email Addresses Analyzed shows the total quantity of contacts in the business unit or unique email addresses in the tenant.
On the mobile dashboard, Total Contacts Analyzed shows the same information.

252
Marketing Cloud Einstein and Analytics Einstein Send Time Optimization

• Assigned Personalized Send Time shows how many contacts or email addresses Einstein can suggest a send time for.
• Pending Personalized Send Time shows how many contacts Einstein needs more data to suggest a send time for. These unmodeled
subscribers receive messages according to a generalized model that is derived from sending data in your Enterprise.
• Data Quality shows 1–5 dots, with the filled dots indicating your Enterprise’s data quality score for email or mobile sending. Expand
the section to access the scores that are considered when generating your data quality score and tips to improve it. Find out more
about data quality scores on the Gauge Your Enterprise Data Quality page.
• The When Are Contacts Likely to Engage with Messages section shows the delivery times during the week when contacts are most
likely to engage with your messages. Einstein assigns a prediction score to each email address or mobile contact. Einstein gives a
0–100 probability score for all 168 hours in a week. The prediction score anticipates the best hour of the week to send to a contact.
This chart aggregates the prediction scores that Einstein assigns to each contact. The chart aggregates scores so it can show the
single hour-day combination with the highest probability to promote message engagement. Enter a contact key to find the optimal
send time for a single contact.

Important: Searching for optimal send time for a single contact is available in the Enterprise-level parent business unit only.
Users in child business units can’t access this data in other business units.

• The When Would Einstein Send section shows the total number or contacts or email addresses in your business unit or Enterprise
account. This section also shows the optimal send times by hour for a day or for all days of the week.
• If you update the Enterprise-level Time Zone for Einstein Send Time Optimization in Setup, the updated Time Zone on the Dashboard
can take up to a week to appear. The time zone setting for the Enterprise level is separate from the Business Unit time zone. Changing
the Business Unit time zone doesn’t affect the Einstein Send Time Optimization dashboard time zone.

SEE ALSO:
Gauge Your Einstein Send Time Optimization Data Quality

Gauge Your Einstein Send Time Optimization Data Quality

Check your Enterprise’s data quality score for insight about the engagement data that Einstein uses to predict optimal send times. Data
quality scores for Einstein Send Time Optimization are generated at the Enterprise level only.
Each Enterprise’s data quality score for email is generated by analyzing the Enterprise’s engagement data. This analysis determines a
send time coverage score and a data richness score. On the Einstein Send Time Optimization (STO) dashboard for mobile, the send time
coverage score is replaced with a mobile send coverage score.

253
Marketing Cloud Einstein and Analytics Einstein Send Time Optimization

• To determine the send time coverage score and mobile send coverage score, Einstein analyzes the number of hours in a week during
which you have at least one send. When your sends are spread across more hours during the week, your send time coverage score
is higher. When your sends happen during fewer hours, your send time coverage score is lower.
• To determine the data richness score, Einstein analyzes the amount and quality of engagement data that’s used to make predictions
for each individual contact. Einstein analyzes only mobile send data to determine the mobile data richness score and only email
send data to determine email data richness.
To find your data quality score, navigate to Einstein Send Time Optimization and view the dashboard. To see your scores and tips that
can help raise your data quality score, click Data Quality Score.

Note: Transactional sends and test sends are excluded when generating your data quality score.

SEE ALSO:
Einstein Send Time Optimization for Email Model Card
Evolve Your Marketing Strategy with Artificial Intelligence

Einstein Send Time Optimization for Email Model Card

The model in this card analyzes the optimal time to send an email to a subscriber to maximize the probability of the subscriber opening
the email.

1. Model Details
The Marketing Cloud Einstein Send Time Optimization model maximizes customer engagement using optimal send times for email
content using these training algorithms, parameters, fairness constraints, features, and other applied approaches.
2. Intended Use
The Marketing Cloud Einstein Send Time Optimization model is intended for these use cases.
3. Relevant Factors
These factors are associated with the Marketing Cloud Einstein Send Time Optimization model.
4. Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance
measures are associated with the Marketing Cloud Einstein Send Time Optimization model. Customers are responsible for monitoring
the accuracy of Einstein Send Time Optimization.
5. Training Data
You have a customized version of the model that’s trained on your data alone, unless you’re opted in to use global model data. Data
from one Salesforce customer doesn’t affect the behavior for another Salesforce customer. While model training happens for each
customer on their data, the initial development of the model is validated with a representative set of pilot customers’ data.
6. Ethical Considerations
Review ethical factors associated with the Marketing Cloud Einstein Send Time Optimization model. To avoid bias and other ethical
risks, the Einstein Send Time Optimization model doesn’t include demographic data.
7. Refresh Cadence
Understand the refresh cadence associated with the Marketing Cloud Einstein Email Engagement Scoring model.

Model Details
The Marketing Cloud Einstein Send Time Optimization model maximizes customer engagement using optimal send times for email
content using these training algorithms, parameters, fairness constraints, features, and other applied approaches.

254
Marketing Cloud Einstein and Analytics Einstein Send Time Optimization

Person or Organization
Salesforce Marketing Cloud Einstein

Model Date and Version

• October 2021
• Minor changes can occur throughout the release
• Major changes can occur and are communicated via release notes

Model Type
• Recommendation/Prediction, Latent factor matrix factorization

General Information
• Einstein Send Time Optimization (STO) is the Salesforce Marketing Cloud solution to maximize the engagement rate of email sends
based on the send time.
• The model chooses the optimal time to send an email to the subscriber to maximize the probability of the subscriber engaging with
the message. Because customer sending patterns vary greatly, we developed parameter sets that are best suited for different patterns.
During training, a parameter selector determines the set chosen for the particular enterprise. The parameter selector bases its decision
on the variation of the sending and engagement patterns over 90 days of history.
• A subscriber who doesn’t have at least one engagement event in the past 90 days is designated as pending a personalized send
time. The model sends to these subscribers according to the Insufficient Data option that their admin selects in Setup.
– The Send at Einstein’s optimal default time option means that Einstein aggregates scores for all of your subscribers that have
sufficient data, creating a distribution of scores for every hour. Einstein STO then uses this distribution to assign scores randomly
to subscribers who lack sufficient data. Such a subscriber can be assigned any optimal default time, but they’re more likely to
be assigned an optimal default time that has a higher score than one that has a lower score. Randomization prevents each
subscriber that’s pending a personalized send time from receiving an email at the same time, which helps avoid sending spikes
and helps Einstein STO get better data.
– The Send immediately option means that subscribers who are pending a personalized send time are sent an email immediately
when they reach the STO activity.
– Subscribers with adequate data are assigned a personalized send time. The model sends at one of the top three hours for each
subscriber. Einstein STO randomly selects a single hour to send according to the distribution of the top three scores. Randomization
allows Einstein STO to constantly monitor which hours can be better for sending and improve send time selection.

• Salesforce customers have the option to contribute to and benefit from global modeling by opting in or out in Marketing Cloud
Setup.
• – For customers that opt in, global modeling is applied when recommending personalized optimal send times, where other
tenants' data can participate in the analysis and modeling process. The global model can use richer information provided by the
opted-in data pool while emphasizing the local tenant’s characteristics in each individual recommendation.
– Individual subscribers who already have strong engagement patterns in the local tenant are influenced less by the global model.
Conversely, individual subscribers who don’t have strong engagement patterns in the local tenant are influenced more by the
global model.
– Customers that opt in contribute data to global modeling. No additional data fields are required for customers using the global
model. Contributed data is de-identified and aggregated at both the tenant and contact levels before being used in local orgs.
In this way, STO’s global model is conducted without sharing personal data, such as email addresses, between tenant instances.
– For customers that opt out, the customer’s model is trained only using that customer’s data.

255
Marketing Cloud Einstein and Analytics Einstein Send Time Optimization

– Send Time Optimization for Marketing Cloud Account Engagement (Pardot) isn’t included in global modeling.

• Einstein STO analyzes the past 90 days of email engagement history of all subscribers within the enterprise (top-level tenant in SFMC
Email Studio).

License
Einstein Send Time Optimization is available to Salesforce Marketing Cloud customers with these editions.
• Corporate Edition
• Enterprise Edition
• Enterprise+ Edition
• Pro Edition where customer also has Journey Builder for Pro Edition SKU
• Einstein Send Time Optimization SKU

256
Marketing Cloud Einstein and Analytics Einstein Send Time Optimization

Questions or Comments
Send questions or comments about the model to mce-support@salesforce.com.

Intended Use
The Marketing Cloud Einstein Send Time Optimization model is intended for these use cases.

Primary Intended Uses

The Send Time Optimization model powers the Einstein Send Time Optimization (STO) activity in Marketing Cloud Journey Builder.
Journey Builder is a tool that marketing professionals use to increase effectiveness in their email marketing campaigns.

Out-of-Scope Use Cases

Anything other than the primary use case is out of scope and not recommended. For example, reducing overall send latency for reservation
booking emails isn’t an intended use case.

SEE ALSO:
Einstein Send Time Optimization for Journey Builder

Relevant Factors
These factors are associated with the Marketing Cloud Einstein Send Time Optimization model.

Model Input
Einstein Send Time Optimization analyzes up to 90 days of historical engagement patterns. The engagement history includes these
factors.
• Email sends, bounces, and engagement events including open, click, and unsubscribe, spam complaints, and associated timestamps
• Data and metadata about customer sending patterns, including how campaigns are executed
The engagement history that Einstein STO analyzes excludes these factors
• Data purchased or collected from third parties
• Demographic Data, which is typically stored in SFMC as data extensions or subscriber or contact attributes
• Specific content within the email template or rendered email body
• Transactional emails such as purchase confirmations, password resets, and others aren’t included

Groups
The model doesn’t include any demographic data or other data purchased from third-party data providers. The model uses engagement
data such as Opens, Sends, and patterns.

Environment
The model is trained and deployed in the Salesforce Marketing Cloud environment.

SEE ALSO:
Infrastructure and Sub-processors for the Salesforce Marketing Cloud Services

257
Marketing Cloud Einstein and Analytics Einstein Send Time Optimization

Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance measures
are associated with the Marketing Cloud Einstein Send Time Optimization model. Customers are responsible for monitoring the accuracy
of Einstein Send Time Optimization.

Model Performance Measures

Aggregated model performance metrics are gathered to monitor, ensure, and improve the quality of the model. Model performance
metrics included the spread and sparsity of input metrics and the correlation of output scores to historical observations. All metrics are
aggregated and anonymized.

Training Data
You have a customized version of the model that’s trained on your data alone, unless you’re opted in to use global model data. Data
from one Salesforce customer doesn’t affect the behavior for another Salesforce customer. While model training happens for each
customer on their data, the initial development of the model is validated with a representative set of pilot customers’ data.
See Global Model Data on page 219 for details about global models and training data.
In general, to provide recommendations Salesforce requires at least one engagement event, such as opens or clicks, of a commercial
email in the past 90 days.

SEE ALSO:
Model Details
Model Details

Ethical Considerations
Review ethical factors associated with the Marketing Cloud Einstein Send Time Optimization model. To avoid bias and other ethical risks,
the Einstein Send Time Optimization model doesn’t include demographic data.
However, biased use of Send Time Optimization can still introduce bias to your marketing process.

Example: A Salesforce customer could use Send Time Optimization for everyone except a vulnerable or disadvantaged segment
of the population. Content sent to the vulnerable segment isn’t send-time-optimized while the rest of the population’s content
is. This use can cause that segment to be further disadvantaged or miss critical marketing communication.

Refresh Cadence
Understand the refresh cadence associated with the Marketing Cloud Einstein Email Engagement Scoring model.

Scores and Models

Einstein Engagement Scoring scores and models for email are updated approximately weekly. The refresh cadence varies by one to
several days based on a customer's individual business unit.

Einstein Send Time Optimization for Mobile Model Card

The model in this card analyzes the optimal time to send a mobile message to maximize a contact’s probability of interacting with it.
Einstein Send Time Optimization for Mobile is the Salesforce Marketing Cloud solution to optimize notification push time in order to
maximize the overall engagement of mobile apps.

258
Marketing Cloud Einstein and Analytics Einstein Send Time Optimization

1. Model Details
The Marketing Cloud Einstein Send Time Optimization model optimizes customer engagement with email content using these
training algorithms, parameters, fairness constraints, features, and other applied approaches.
2. Intended Use
The Marketing Cloud Einstein Send Time Optimization for Mobile model is intended for these use cases.
3. Relevant Factors
These factors are associated with the Marketing Cloud Einstein Send Time Optimization for Mobile model.
4. Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance
measures are associated with the Marketing Cloud Einstein Send Time Optimization model. Customers are responsible for monitoring
the accuracy of Einstein Send Time Optimization.
5. Training Data
You have a customized version of the model that’s trained on your data alone. Data from one Salesforce customer doesn’t affect the
behavior for another Salesforce customer. While model training happens for each customer on their data, the initial development
of the model is validated with a representative set of pilot customers’ data.
6. Ethical Considerations
Review the ethical factors associated with the Marketing Cloud Einstein Send Time Optimization for Mobile model. To avoid bias
and other ethical risks, the Einstein Send Time Optimization for Mobile model doesn’t include demographic data.
7. Refresh Cadence
Understand the refresh cadence associated with the Marketing Cloud Einstein Email Engagement Scoring model.

Model Details
The Marketing Cloud Einstein Send Time Optimization model optimizes customer engagement with email content using these training
algorithms, parameters, fairness constraints, features, and other applied approaches.

Person or Organization
Salesforce Marketing Cloud Einstein

Model Date and Version

• December 2020
• Minor changes can occur throughout the release
• Major changes can occur and are communicated via release notes

Model Type
• Recommendation/Prediction, Latent factor matrix factorization

General Information
• Einstein Send Time Optimization for Mobile is Salesforce Marketing Cloud’s solution to optimize notification push time in order to
maximize the overall engagement of mobile apps.
• The model chooses the optimal time to send a push notification to the contact to maximize the probability of the contact engaging
with the app. Contacts engage either by tapping on the push notification to open the app or launching the app directly. The model

259
Marketing Cloud Einstein and Analytics Einstein Send Time Optimization

also detects individual in-app patterns to avoid sending push notifications when contacts are already in the app. A contact can have
different optimal send time for different apps.
• We train each customer’s model only using that customer’s data.
• A contact who doesn’t have enough data is part of the Pending Personalized Send Time group. A contact is categorized as not having
enough data when there isn’t at least 1 open in the past 90 days. For these contacts, the model defaults to send one of two ways
based on Insufficient Data Option that the admin has selected in the STO Setup page.
• The two options are Send at Einstein’s optimal default time and Send immediately. When you select Send at Einstein’s optimal
default time, Einstein aggregates across all of your contacts that do have sufficient data to create a distribution of scores across every
hour. Einstein then follows this distribution of scores to randomly assign scores to contacts who don’t have enough data. So a contact
who doesn’t have enough data could get assigned any optimal default time, but they’re more likely to get assigned an optimal
default time that has a higher score than one that has a lower score. This randomization is added in so that everyone in the Pending
Personalized Send Time group doesn’t receive their email at the same time, which helps avoid spikes as well as helps Einstein get
better data.
• Contacts in the Pending Personalized Send Time group are sent a push notification immediately when they reach the STO activity.

License
Einstein Send Time Optimization for Mobile is available to Salesforce Marketing Cloud customers with these editions.
• Corporate Edition
• Enterprise Edition
• Enterprise+ Edition
• Pro Edition where customer also has Journey Builder for Pro Edition SKU
• Einstein Send Time Optimization SKU

Questions or Comments
Send questions or comments about the model to mce-support@salesforce.com.

Intended Use
The Marketing Cloud Einstein Send Time Optimization for Mobile model is intended for these use cases.

Primary Intended Uses

The Send Time Optimization model powers the Einstein Send Time Optimization (STO) activity in Marketing Cloud Journey Builder.
Journey Builder is a tool that marketing professionals use to increase effectiveness in their mobile marketing campaigns.

Out-of-Scope Use Cases

Anything other than the primary use case is out of scope and not recommended. For example, reducing overall send latency for reservation
booking mobile messages isn’t an intended use case.

Relevant Factors
These factors are associated with the Marketing Cloud Einstein Send Time Optimization for Mobile model.

260
Marketing Cloud Einstein and Analytics Einstein Send Time Optimization

Model Input
Einstein Send Time Optimization for Mobile analyzes up to 90 days of historical engagement patterns. The engagement history includes
these factors.
• Push events and reactions, such as push notifications and taps on push notifications, and associated timestamps
• Data and metadata about customer sending patterns and how campaigns are executed
The engagement history that Einstein STO analyzes excludes these factors
• Data purchased or collected from third parties
• Demographic Data, which is typically stored in SFMC as data extensions or subscriber or contact attributes
• Specific content within the push template or rendered push message body

Groups
The model doesn’t include any demographic data or other data purchased from third-party data providers. The model uses mobile
engagement data such as Push, TapOpen, AppOpen, or TimeInApp.

Environment
The model is trained and deployed in the Salesforce Marketing Cloud environment.

Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance measures
are associated with the Marketing Cloud Einstein Send Time Optimization model. Customers are responsible for monitoring the accuracy
of Einstein Send Time Optimization.

Model Performance Measures

Aggregated model performance metrics are gathered to monitor, ensure, and improve the quality of the model. Model performance
metrics included the spread and sparsity of input metrics and the correlation of output scores to historical observations. All metrics are
aggregated and anonymized.

Training Data
You have a customized version of the model that’s trained on your data alone. Data from one Salesforce customer doesn’t affect the
behavior for another Salesforce customer. While model training happens for each customer on their data, the initial development of the
model is validated with a representative set of pilot customers’ data.
In general, to provide recommendations Salesforce requires at least one engagement event, such as opens or clicks, of a commercial
email in the past 90 days.

Ethical Considerations
Review the ethical factors associated with the Marketing Cloud Einstein Send Time Optimization for Mobile model. To avoid bias and
other ethical risks, the Einstein Send Time Optimization for Mobile model doesn’t include demographic data.
However, biased use of Send Time Optimization (STO) for Mobile can still introduce bias to your marketing process.

Example: A Salesforce customer could use STO for everyone except a vulnerable or disadvantaged segment of the population.
Content sent to the vulnerable segment isn’t send-time optimized, while the rest of the population’s content is. This use can cause
that segment to be further disadvantaged or miss critical marketing communication.

261
Marketing Cloud Einstein and Analytics Einstein Engagement Frequency

Refresh Cadence
Understand the refresh cadence associated with the Marketing Cloud Einstein Email Engagement Scoring model.

Scores and Models

Einstein Engagement Scoring scores and models for email are updated approximately weekly. The refresh cadence varies by one to
several days based on a customer's individual business unit.

Einstein Engagement Frequency

Avoid a lack of awareness from too few messages or burnout from too many messages. Einstein Engagement Frequency in Marketing
Cloud evaluates your contacts and subscribers and identifies the optimal number of email messages to send.

Considerations
Einstein Engagement Frequency (EEF) optimizes send frequency for each individual contact, maximizing engagement rates and reducing
unsubscribes.
• Engagement frequency metrics are derived from the past 28 days' data.
• Only commercial emails are analyzed. Transactional and test sends aren’t analyzed.
• A minimum of five frequencies is required, which means that the audience in your business unit must receive at least five variants
of your email messaging over a 28-day period. For EEF, a variant is defined as an email sending pattern, which is sending email to
subscribers in at least five different intervals.

Example: A fundraising professional uses Einstein Engagement Frequency to make sure that they can reach supporters by sending
each supporter the optimal number of emails. The fundraiser has learned that some supporters give only one time, some give
regularly, and some give on specific occasions. Some haven’t yet donated. The fundraiser also divides supporters according to the
size of their contributions. The fundraiser divides the supporters into seven categories. Each category is placed in one of seven
paths in a journey. To reach each category of supporters, the fundraiser sends email to each category on a different day and at a
different time. By varying the sending for each category, the fundraiser creates seven sending variants.
When the fundraiser analyzes the Einstein Engagement Frequency analytics, they see message engagement results as expected.
And because Einstein makes better predictions when more data is available, the fundraiser can expect their predictions to become
more accurate.

Example: An email marketer sends a weekly newsletter to their organization’s customers. The marketer sends using a journey
and uses a data extension that includes all the organization’s subscribers as the entry source for each send. The journey includes
a Frequency Split activity before the email activity that sends the newsletter. But when the marketer views the journey’s activity
analytics, they see no results.
And it’s because they send only one time a week. The marketer sees unexpected results because by sending once a week to an
audience that includes all their customers, they’re using only one sending variant. They don’t meet the minimum of five frequencies
to send to their subscribers.

Note: Einstein Engagement Frequency provides the optimized range for your entire email messaging frequency. This range
includes all campaigns and subscribers involved in your email messaging activities.
21

21
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

262
Marketing Cloud Einstein and Analytics Einstein Engagement Frequency

Activate Einstein Engagement Frequency

Activate Einstein Engagement Frequency (EEF) at the MID level for your account. The activation process can take up to 72 hours to
complete. Provision Journey Builder before you use Einstein Engagement Frequency. To use EEF for MobilePush, first provision
Journey Builder and create at least one mobile app.
The Einstein Engagement Frequency Dashboard
Use the dashboard to get an overview of sending saturation levels among your contacts. Then analyze the way that your sending
frequency affects your contacts’ saturation levels. You can review how your sending frequency has affected engagement including
opens, clicks, and unsubscribes, over time. Use the What-If analyzer to help maximize your On Target saturation contact levels. See
how contacts are performing across all your journeys.
Gauge Your Einstein Engagement Frequency Data Quality
Check your data quality score for insight about the engagement data that Einstein uses to predict your customers’ likelihood to
engage. Data quality scores for Einstein Engagement Frequency are generated at the business unit level only.
Einstein Engagement Frequency Model Card
The model in this card analyzes each contact’s engagement record to determine the optimal frequency at which to send email
messages to that contact.
Einstein Engagement Frequency FAQs
Find out how Journey Builder access affects Einstein Engagement Frequency use. And get informed about what happens to your
older send frequency data after you upgrade to the latest Einstein Engagement Frequency experience.

Activate Einstein Engagement Frequency

Activate Einstein Engagement Frequency (EEF) at the MID level for your account. The activation process can take up to 72 hours to
complete. Provision Journey Builder before you use Einstein Engagement Frequency. To use EEF for MobilePush, first provision Journey
Builder and create at least one mobile app.

Note: If your organization uses Einstein Engagement Frequency before the October 2020 Einstein Engagement Frequency
upgrade, activating the updated version of the app removes the Einstein_MC_EMAIL_Frequency_Undersaturation and
Einstein_MC_Email_Frequency_Oversaturation data extensions.
1. Navigate to Marketing Cloud Setup.
2. Click Einstein.
3. Click Einstein Engagement Frequency.
4. Select the Email or MobilePush tab.
5. Click Activate Einstein Engagement Frequency.
6. If you’re turning on EEF for MobilePush, select the apps to activate.
a. To deactivate an app, click and click Deactivate.
22

22
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

263
Marketing Cloud Einstein and Analytics Einstein Engagement Frequency

The Einstein Engagement Frequency Dashboard

Use the dashboard to get an overview of sending saturation levels among your contacts. Then analyze the way that your sending
frequency affects your contacts’ saturation levels. You can review how your sending frequency has affected engagement including
opens, clicks, and unsubscribes, over time. Use the What-If analyzer to help maximize your On Target saturation contact levels. See how
contacts are performing across all your journeys.
To access the Einstein Engagement Frequency Dashboard, go to Einstein, and click Einstein Engagement Frequency. Click Email or
Mobile. When you click the mobile dashboard, select the app whose analytics you want to see.
Find out how strong your data quality is for email or mobile engagement frequency. Click View Details at the top of the dashboard for
data quality scores and tips to improve.

Note: When one or more contacts don’t have enough data for Einstein to assign a frequency score, Einstein assigns the score
according to global model data. In this case, analytics on the Einstein Engagement Frequency dashboard sometimes don’t match
activity-level analytics in a journey.

What-If Analyzer
Test future saturation levels corresponding to message frequency using the What-If Analyzer on the Einstein Engagement Frequency
dashboard. The goal is to maximize the On Target contacts in your business unit. Use the bar chart to predict how many contacts
you can move from Saturated or Undersaturated to On Target.

What-If Analyzer
Test future saturation levels corresponding to message frequency using the What-If Analyzer on the Einstein Engagement Frequency
dashboard. The goal is to maximize the On Target contacts in your business unit. Use the bar chart to predict how many contacts you
can move from Saturated or Undersaturated to On Target.
Choose one of the dropdown menu options, and use the bar graph to view scenarios. Based on a 7-day outlook, Einstein Insight
recommends the optimal number of messages to send to move contacts to On Target. Click the graph bars for details including the
number of contacts in each saturation level based on the number of messages for the bar you chose. The number of messages on the
bar is the number of messages to send to the source segment you selected in the dropdown. For example, if you chose Undersaturated
to On Target, the number on the bar graph indicates the number of messages to send to the Undersaturated contacts.

Example: You want to determine how many messages to send to your Undersaturated contacts to move them to On Target.
Einstein recommends sending three more messages within 7 days of the last update. For comparison, you click other message
numbers in the bar graph to see the projected results. After you determine the optimal number of messages to send, add a
frequency split in the journey and add the optimal number of messages.

Gauge Your Einstein Engagement Frequency Data Quality

Check your data quality score for insight about the engagement data that Einstein uses to predict your customers’ likelihood to engage.
Data quality scores for Einstein Engagement Frequency are generated at the business unit level only.
Each business unit’s data quality score for email is generated by analyzing the business unit’s engagement data. This analysis determines
a Frequency Density score and an Engagement Frequency Rate score.
• To determine the Frequency Density score, Einstein analyzes the different cadences of sending frequencies in your business unit,
comparing the areas of highest concentration of this business unit’s sending frequencies to the maximum sending frequency in
your account. When you send messages to different customer segments at different cadences, you create a variety of send frequencies.
To generate engagement frequency scores send to at least five customer segments.
• To determine the Engagement Frequency Rate score, Einstein analyzes how often contacts in your business unit engage with a
message that’s part of a distinct sending frequency. Einstein compares this rate to the number of sending frequencies that the same

264
Marketing Cloud Einstein and Analytics Einstein Engagement Frequency

contact has experienced. This score helps Einstein understand how your contacts engage with emails across different sending
frequencies.
To find your data quality score, navigate to the Einstein Engagement Frequency dashboard. To see your scores and tips that can help
raise your data quality score, click Data Quality Score.

Note: Transactional sends and test sends are excluded when generating your data quality score.

SEE ALSO:
Einstein Engagement Frequency Model Card
Evolve Your Marketing Strategy with Artificial Intelligence

Einstein Engagement Frequency Model Card

The model in this card analyzes each contact’s engagement record to determine the optimal frequency at which to send email messages
to that contact.

1. Model Details
The Marketing Cloud Einstein Engagement Frequency model optimizes the frequency of customer engagement with email content
using these training algorithms, parameters, fairness constraints, and features.
2. Intended Use
The Marketing Cloud Einstein Engagement Frequency model is intended for these use cases.
3. Relevant Factors
These factors are associated with the Marketing Cloud Einstein Engagement Frequency model.
4. Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance
measures are associated with the Marketing Cloud Einstein Engagement Frequency model.
5. Training Data
You have a customized version of the model that’s trained on your data alone. Data from one Salesforce customer doesn’t affect the
behavior for another Salesforce customer. While model training happens for each customer on their data, the initial development
of the model is validated with a representative set of pilot customers’ data.
6. Ethical Considerations
Review ethical factors associated with the Marketing Cloud Einstein Engagement Frequency model. To avoid bias and other ethical
risks, the Einstein Engagement Frequency model doesn’t include demographic data.
7. Refresh Cadence
Review the refresh cadence associated with the Marketing Cloud Einstein Email Engagement Frequency model.

Model Details
The Marketing Cloud Einstein Engagement Frequency model optimizes the frequency of customer engagement with email content
using these training algorithms, parameters, fairness constraints, and features.

Person or Organization
Salesforce Marketing Cloud Einstein

265
Marketing Cloud Einstein and Analytics Einstein Engagement Frequency

Model Date and Version

• May 2020
• Minor changes can occur throughout the release
• Major changes can occur and are communicated via release notes

Model Type
Matrix factorization, Recommendation system

General Information
Einstein Engagement Frequency (EEF) helps marketers determine the right number of emails to send to individual subscribers of an
organization, reducing the unsubscribes that result from email fatigue. Marketers can use EEF to identify opportunities to further engage
subscribers with emails. The model analyzes individual subscribers’ historical engagement patterns over different frequencies. And it
uses data of other users with similar patterns to help complete and adjust the scoring of each frequency. The ideal frequency range of
each individual is then calculated based on those scores to help find the best frequency band that maximizes engagement. Salesforce
trains each customer’s model using only that customer’s data.

Constraints
• A minimum of 10 subscribers is required to model for engagement frequency.
• A minimum of five frequencies is required to model for engagement frequency. The audience in your business unit must receive at
least five variants of your email messaging over a 28-day period. For EEF, a variant is defined as an email sending pattern, which is
sending email to subscribers with at least five different intervals.

License
Einstein Engagement Frequency is available to Salesforce Marketing Cloud customers with any of these editions.
• Corporate Edition
• Enterprise Edition
• Enterprise+ Edition

Questions or Comments
Send questions or comments about the model to mce-support@salesforce.com.

Intended Use
The Marketing Cloud Einstein Engagement Frequency model is intended for these use cases.

Primary Intended Uses

The Einstein Engagement Frequency model powers the Frequency split activity in Marketing Cloud Journey Builder. The Frequency split
activity is designed for marketing professionals to send the optimal number of emails to every subscriber in their business unit, reducing
subscriber email fatigue. The feature predicts the optimal number of emails to send an individual contact, maximizing their engagement
rate, across all campaigns, and email types, within a business unit.

266
Marketing Cloud Einstein and Analytics Einstein Engagement Frequency

Out-of-Scope Use Cases

Anything other than the primary use case is out of scope and not recommended. For example, prioritizing which emails to send to
subscribers based on their current saturation level, and manually capping the email send frequency per campaign aren’t intended use
cases.

Relevant Factors
These factors are associated with the Marketing Cloud Einstein Engagement Frequency model.

Model Input
Einstein Engagement Frequency analyzes up to 90 days of historical engagement patterns of the subscribers. The engagement history
includes these factors.
• Email sends, bounces, and engagement events including open, click, and unsubscribe, spam complaints, and associated timestamps
• Data and metadata about customer sending patterns, including how campaigns are executed
The engagement history that Einstein Engagement Frequency analyzes excludes these factors.
• Data purchased or collected from third parties
• Demographic Data, which is typically stored in SFMC as data extensions or subscriber or contact attributes
• Specific content within the email template or rendered email body

Model Output
• The model produces a personalized ideal frequency band for each active subscriber and an overall Business Unit-level ideal frequency
band.

Groups
The model doesn’t include demographic data or other data purchased from third-party data providers. The model uses engagement
data such as opens, sends, and patterns.

Environment
The model is trained and deployed in the Salesforce Marketing Cloud environment.

SEE ALSO:
Infrastructure and Sub-processors for the Salesforce Marketing Cloud Services

Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance measures
are associated with the Marketing Cloud Einstein Engagement Frequency model.

Model Performance Measures

Model performance metrics include metrics like the spread and sparsity of input metrics and the correlation of output scores to historical
observations. All metrics are aggregated and anonymized.

267
Marketing Cloud Einstein and Analytics Einstein Engagement Frequency

Training Data
You have a customized version of the model that’s trained on your data alone. Data from one Salesforce customer doesn’t affect the
behavior for another Salesforce customer. While model training happens for each customer on their data, the initial development of the
model is validated with a representative set of pilot customers’ data.

SEE ALSO:
Model Details

Ethical Considerations
Review ethical factors associated with the Marketing Cloud Einstein Engagement Frequency model. To avoid bias and other ethical risks,
the Einstein Engagement Frequency model doesn’t include demographic data.

Refresh Cadence
Review the refresh cadence associated with the Marketing Cloud Einstein Email Engagement Frequency model.

Scores and Models

Einstein Engagement Frequency scores and models for email are updated weekly. The refresh cadence varies by one to several days
based on a customer's individual business unit.

Einstein Engagement Frequency FAQs

Find out how Journey Builder access affects Einstein Engagement Frequency use. And get informed about what happens to your older
send frequency data after you upgrade to the latest Einstein Engagement Frequency experience.

To Use Einstein Engagement Frequency’s Updated Version, Do I Need Journey Builder?

Yes. Journey Builder must be provisioned in accounts that plan to use the updated Einstein Engagement Frequency app. Find account
provisioning information in the Journey Builder Prerequisites.
Does Updating to the New Version of Einstein Engagement Frequency Remove My Old Data?
Yes. Updating the app removes older data used by Einstein Engagement Frequency. Specifically, the two data extensions populated
by Einstein Engagement Frequency, called Einstein_MC_EMAIL_Frequency_Undersaturation and
Einstein_MC_Email_Frequency_Oversaturation, are deleted. No other data extensions are deleted or modified.
Can Einstein Predict Engagement Frequency on a Segment or Brand Level?
No. Engagement frequency predictions are only available at the contact level for contacts in your business unit.
Are Saturated Contacts Suppressed from Email Sends?
No. Einstein Engagement Frequency identifies segments and groups your contacts by segment, but you control sending. To prevent
saturated contacts from receiving unwanted messages, remove or reduce messaging activities in their journey path.
Does Einstein Predict Engagement Frequency for Mobile Products?
Yes. Einstein Engagement Frequency supports email and MobilePush.

268
Marketing Cloud Einstein and Analytics Einstein Copy Insights

To Use Einstein Engagement Frequency’s Updated Version, Do I Need Journey Builder?

Yes. Journey Builder must be provisioned in accounts that plan to use the updated Einstein Engagement Frequency app. Find account
provisioning information in the Journey Builder Prerequisites.

SEE ALSO:
Journey Builder Prerequisites

Does Updating to the New Version of Einstein Engagement Frequency Remove My Old Data?
Yes. Updating the app removes older data used by Einstein Engagement Frequency. Specifically, the two data extensions populated by
Einstein Engagement Frequency, called Einstein_MC_EMAIL_Frequency_Undersaturation and
Einstein_MC_Email_Frequency_Oversaturation, are deleted. No other data extensions are deleted or modified.

SEE ALSO:
Activate Einstein Engagement Frequency

Can Einstein Predict Engagement Frequency on a Segment or Brand Level?

No. Engagement frequency predictions are only available at the contact level for contacts in your business unit.

Are Saturated Contacts Suppressed from Email Sends?

No. Einstein Engagement Frequency identifies segments and groups your contacts by segment, but you control sending. To prevent
saturated contacts from receiving unwanted messages, remove or reduce messaging activities in their journey path.

Does Einstein Predict Engagement Frequency for Mobile Products?

Yes. Einstein Engagement Frequency supports email and MobilePush.

Einstein Copy Insights

Einstein Copy Insights uses text analytics and natural language processing to analyze the text from your commercial email subject lines
to uncover language insights. Use these insights to craft subject lines that drive stronger email engagement. With the performance
tester you can find out how your subject line is likely to affect a message’s engagement rate by comparing it to past subject lines and
their engagement rates. You can evaluate a single subject line or compare up to 10 different subject lines.

Considerations
• Einstein Copy Insights assesses a 90-day rolling window of email engagement data to produce insights.
• Einstein Copy Insights are updated one time each week.
• Insights are available for English subject lines only.
• Insights are based on email engagement rates.
• To populate the model, Einstein Copy Insights requires at least 10 different subject lines sent to at least 30 subscribers within a 30-day
period.

269
Marketing Cloud Einstein and Analytics Einstein Copy Insights

23

Set Up Einstein Copy Insights

Einstein Copy Insights is on by default in all business units in an enterprise that enables it. All users in the business unit can view the
insights. To allow analysis, automation moves data to the Marketing Cloud’s Einstein Platform.
View Einstein Copy Insights
To review insights and find the word and phrase combinations that drive better email engagement, navigate to the insights hub.
Subject Line Groups
Einstein analyzes most of your commercial subject lines in order to detect and surface interesting insights and patterns in the language
that you use.
Einstein Subject Line Tester Model Card
The model in this card analyzes and evaluates contact engagement based on email subject lines.
Subject Line Tester
Find out how your message’s subject line is likely to influence message performance. Test the performance of a single message or
compare up to 10 subject lines. The Subject Line Tester is available only if you opt in to global models.

Set Up Einstein Copy Insights

Einstein Copy Insights is on by default in all business units in an enterprise that enables it. All users in the business unit can view the
insights. To allow analysis, automation moves data to the Marketing Cloud’s Einstein Platform.
1. Navigate to Marketing Cloud Setup.
2. Click Einstein.
3. Click Einstein Copy Insights.
4. Activate Einstein Copy Insights for your business unit.

View Einstein Copy Insights

To review insights and find the word and phrase combinations that drive better email engagement, navigate to the insights hub.
1. Click Einstein.
2. Click Einstein Copy Insights.

Note: Einstein Copy Insights are updated once each week.

Einstein Copy Insights Dashboard

Review insights about the subject lines that your organization’s emails use and test subject lines that you plan to include in upcoming
messages. See top performing and most used subject lines, as well as insights derived from language factors, emotional tone, and
phrases within a subject line.

23
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

270
Marketing Cloud Einstein and Analytics Einstein Copy Insights

Einstein Copy Insights Dashboard

Review insights about the subject lines that your organization’s emails use and test subject lines that you plan to include in upcoming
messages. See top performing and most used subject lines, as well as insights derived from language factors, emotional tone, and phrases
within a subject line.
Use the Einstein Copy Insights dashboard to examine several factors relating to your emails’ subject lines. If you understand how an
email’s subject line affects engagement with the email, you can craft more engaging subject lines to increase engagement.
The subject lines and the associated engagement rates and send totals shown sometimes don’t match the results that appear in other
analytics tools. When Einstein detects similar or identical language, Einstein automatically groups those subject lines together and
calculates a single average engagement rate.

Considerations
• Einstein doesn’t consider transactional, test, or bounced sends.
• Einstein doesn’t consider commercial sends to fewer than 30 subscribers.
• A blank space (___) in a subject line indicates that Einstein has identified and consolidated similar language elements. For example,
proper names, offer values, or product names typically are consolidated.
• Analytics are updated weekly.
• The Performance Tester is available only to customers who opt in to global models.

Dashboard Widget Description

Subject Line Analytics Review best performing subject line language sorted by
engagement rate or number of associated messages sent.

Language Factor Insights Find out which qualities in your subject lines spur engagement.
These insights include an impact metric to show whether the factor
has a positive or negative impact and to what degree this factor
impacts engagement.

Emotional Tone Insights See which emotional tones Einstein finds that your subject line
language aligns with and its impact on performance. The size of
each emotional tone’s circle represents the number of subject lines
that include that tone.

Top Performing Phrases Understand which one-, two-, and three-word phrases in your
subject lines make an impression on subscribers. When you select
a two- or three-word phrase, only the words that appear
consecutively in your subject lines appear.

Most Frequently Used Phrases See which commonly used phrases in your subject lines prompt
engagement and if that engagement is better or worse than the
average engagement rate.

Tip: The emotional tone factor labeled FOMO is the acronym for fear of missing out.

271
Marketing Cloud Einstein and Analytics Einstein Copy Insights

Subject Line Groups

Einstein analyzes most of your commercial subject lines in order to detect and surface interesting insights and patterns in the language
that you use.
When subject lines across multiple sends are identical or similar, Einstein automatically groups them. Then Einstein calculates a single,
unweighted average performance rate to more accurately understand language performance. These grouped subject lines are the
primary input data to all of the Einstein Copy Insights models, including those models used to generate language-related insights and
performance predictions.
Often there’s a correlation between when Einstein detects a similar word or phrase and the AMPscript that’s used, but such a correlation
isn’t guaranteed. Static text isn’t always recognized as unique across sends. AI-driven consolidation happens based on the language
found, regardless of how the subject line was created, when it was sent, or who received it.
For example, the subject line for a product sale can be the same for all recipients except for the name of the product or discount. And
happy birthday messages can be the same except for the recipient’s name. The result of %%firstname%% in Content Builder is consolidated
by the AI..But sometimes results aren’t consolidated if the language used is more complex AMPscript like %%=v(@customSubjectLine)=%%.

Tip: When Einstein groups similar subject lines that appear on-screen as in the Subject Line Analytics widget, the similar words
or phrases are indicated onscreen with ___. For example, you see Happy Birthday ___.
You can see language with AMPscript and ___ in ECI dashboards for up to 90 days after you active ACI. To ensure that we handle your
data with trust top of mind, ECI doesn’t collect fully rendered subject lines until the app is activated. To help decrease the amount of
time it takes to create meaningful results, ECI pulls from a blend of rendered subject lines and subject lines as they appear in Marketing
Cloud. Subject lines can include AMPscript.

Example: A marketer for a global charity uses Journey Builder to manage donation follow-up. They refresh content quarterly,
using AMPscript like %%=v(@customSubjectLine)=%% in their subject line. The marketer can dynamically use one of these three
options based on the type of donation.
• %%firstname%%, your donation counts!
• Thanks for the donation, %%firstname%%.
• We love the love
When Einstein evaluates historical subject line performance each of the three options are considered independently, even though
they can be part of the same send. For example, consider these engagement rates.

Overall Send Engagement Rate 33%

%%firstname%%, your donation counts! 45%

Thanks for the donation, %%firstname%% 22%

We love the love 31%

The unweighted average engagement rate for the send is 33%. But test subject lines are evaluated against the language and
language-specific engagement rates (subject line groups) to determine potential effectiveness.

272
Marketing Cloud Einstein and Analytics Einstein Copy Insights

If the marketer sends a separate one-off email with an identical or similar subject line to one of the three options shown, the subject
lines are grouped. Subject lines are represented one time in Einstein Copy Insights.

SEE ALSO:
Create a Content Test
Global Model Data Opt In and Opt Out

Einstein Subject Line Tester Model Card

The model in this card analyzes and evaluates contact engagement based on email subject lines.

Model Details
The Marketing Cloud Einstein Subject Line Tester model compares and analyzes subject line options with training algorithms,
parameters, fairness constraints, features, and other applied approaches.
Intended Use
The Marketing Cloud Einstein Subject Line Tester model is intended for these use cases.
Relevant Factors
These factors are associated with the Marketing Cloud Einstein Subject Line Tester model.
Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance
measures are associated with the Marketing Cloud Einstein Subject Line Tester model.
Training Data
You have a customized version of the model that’s trained using global model data including in-house data and outsourcing data.
Data from one Salesforce customer doesn’t affect the behavior for another Salesforce customer. Each version of the model uses the
global model data associated with optimized sample weights customized for the corresponding customer.
Ethical Considerations
Review the ethical factors associated with the Marketing Cloud Einstein Subject Line Tester model. To avoid bias and other ethical
risks, the Einstein Subject Line Tester model doesn’t include demographic data.

Model Details
The Marketing Cloud Einstein Subject Line Tester model compares and analyzes subject line options with training algorithms, parameters,
fairness constraints, features, and other applied approaches.

Person or Organization
Salesforce Marketing Cloud Einstein

Model Date and Version

• October 2021
• Minor changes can occur throughout the release
• Major changes can occur and are communicated via release notes

273
Marketing Cloud Einstein and Analytics Einstein Copy Insights

Model Type
• Prediction, Gradient boosted regression trees, Hyper-parameter grid search

General Information
• Einstein Performance Tester for Subject Lines (SLT) is the Salesforce Marketing Cloud’s solution to predict email engagement rate
based on the subject line content provided by customer.
• Analyze a single subject line’s performance or compare up to 10 subject lines at once.
• SLT helps customers understand the potential impact of language used in subject lines and improve the overall engagement of
their subscribers.
• We use the global data pool due to the limited quantity of data a single customer is likely to have for subject line engagement
predictions. We use the global data pool with the customer’s own local data to train the model. Because of this global model, even
customers who have small data samples can take advantage of the performance tester. Customers can opt in or opt out. If a customer
opts in, they contribute to and benefit from global modeling.
• Customer subject line contents vary greatly, so we have an optimal pooling strategy that makes a personalized tradeoff between a
customer’s local data and global data for each customer. To provide the best predictions for the target customers, we put global
data into the model and customize the model. We customize by searching for the hyper-parameters that are best for each customer.
The two primary cases are customers with relatively large subject line samples and customers with relatively small subject line
samples that still meet sample size requirements. In the first case, local data from the customer can already contain rich insights and
patterns. The sample size of the local data can be large enough for modeling. The prediction performance is reasonably good. To
improve the model, we retrieve insights from the global data and feed the additional insights to the model. Then, we take advantage
of local data that represents the customer best. In this case, local data still dominates the performance of the mode. In the second
case, we can retrieve limited insights from their local data and the sample size is small. Therefore, the model trained with the local
data yields high prediction error, so we use the global data for help. In this case, global data dominates the model performance.
• The features used to train the model include historical observations and natural language processing (NLP) features. The features
can be divided into three levels of extractions; Sentence level, Word level, and Symbol or Character level. Sentence level includes
word count, term frequency-inverse document frequency (TD-IDF). Word level includes a call to action, immediacy keyword checker.
Symbol or Character level includes emoji, question mark, exclamation marker, and character count.
• See Global Model Data on page 219 in Salesforce Help for more information.

License
Einstein Performance Tester for Subject Lines is available to Salesforce Marketing Cloud customers with any of these editions and SKUs.
• Corporate Edition
• Enterprise Edition
• Enterprise+ Edition
• Pro Edition where customer also has Journey Builder for Pro Edition SKU
• Einstein Send Time Optimization SKU

Questions or Comments
Send questions or comments about the model to mce-support@salesforce.com.

Intended Use
The Marketing Cloud Einstein Subject Line Tester model is intended for these use cases.

274
Marketing Cloud Einstein and Analytics Einstein Copy Insights

Primary Intended Uses

The Performance Tester model helps customers understand the potential impact of language used in subject lines and predict email
engagement rate to improve the overall subscriber engagement. Evaluate a single subject line or compare up to 10 subject lines.

Out-of-Scope Use Cases

Anything other than the primary use case is out of scope and not recommended.

Relevant Factors
These factors are associated with the Marketing Cloud Einstein Subject Line Tester model.

Model Input
Einstein Subject Line Tester analyzes up to 90 days of historical engagement patterns of the subscribers. The engagement history includes
these factors.
• Email sends, bounces, and engagement events including open, click, and unsubscribe, spam complaints, and associated timestamps
• Email subject lines
The engagement history that Einstein SLT analyzes excludes these factors.
• Data purchased or collected from third parties
• Demographic Data, which is typically stored in SFMC as data extensions or subscriber or contact attributes

Model Output
• The model produces aggregated engagement data by each subject line and generates the average email effectiveness rate per
subject line to train the model.

Groups
The model doesn’t include any demographic data or other data purchased from third-party data providers. The model uses engagement
data and subject line groups data. We use a grouping technique that aggregates similar subject lines to reduce the number of subject
lines that occur from personalization. For example, if your subject line is “Happy Birthday, Jane,” we ignore the personalized name and
use the common subject line text only. This type of aggregation provides a more accurate view of subject line engagement.

Environment
The model is trained and deployed in the Salesforce Marketing Cloud environment.

Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance measures
are associated with the Marketing Cloud Einstein Subject Line Tester model.

Model Performance Measures

• Sample size and contribution ratio of in-house data for each customer are gathered to monitor.
• Root mean squared error (RMSE) between predicted and actual engagement rate for each customer is calculated and tracked.

275
Marketing Cloud Einstein and Analytics Einstein Copy Insights

• Correlations of actual rates to historical observations and natural language processing (NLP) extracted features are calculated and
displayed in the internal dashboard. The model is retrained and updated with new information mined from the data.

Training Data
You have a customized version of the model that’s trained using global model data including in-house data and outsourcing data. Data
from one Salesforce customer doesn’t affect the behavior for another Salesforce customer. Each version of the model uses the global
model data associated with optimized sample weights customized for the corresponding customer.

Ethical Considerations
Review the ethical factors associated with the Marketing Cloud Einstein Subject Line Tester model. To avoid bias and other ethical risks,
the Einstein Subject Line Tester model doesn’t include demographic data.
The model uses the global data model. Subject lines are pooled together based on context. By aggregating the data samples across a
wide range of customers we aim to ensure a degree of fairness for our customers.

Subject Line Tester

Find out how your message’s subject line is likely to influence message performance. Test the performance of a single message or
compare up to 10 subject lines. The Subject Line Tester is available only if you opt in to global models.
In addition to opting in to global models, the Einstein Copy Insights (ECI) dashboard and Subject Line Tester require some information
before making predictions. Your business unit needs at least 10 subject lines with at least 30 deliveries in the last 90 days before Einstein
can provide predictions.
When you evaluate your subject lines using the performance tester, Einstein compares the subject line with most other subject lines
sent over the past 90 days. Einstein evaluates the subject lines as they appear in your subscriber’s inbox, even if you create and personalize
them with AMPscript.
Einstein also tests the subject line for potential bias. Salesforce defines bias as using a person’s immutable traits to classify them or market
to them. If the subject line contains words flagged as introducing potential bias, you can choose to address them before sending the
message.
To help you understand how the predicted performance compares to your own past performance in a business unit, contextual analytics
appear after you test a subject line.
A model confidence score of 1–5 indicates Einstein’s confidence in the model. A score of five indicates the highest confidence rating.
A data quality score of 1–5 indicates how effectively Einstein is using your subject line data for intended use in engagement prediction.
A score of 5 means that your subject lines are effective for the model.

Test a Subject Line Before You Send

Find out how your message’s subject line is likely to influence message performance. Test the performance of a single message or
compare up to 10 subject lines.

Test a Subject Line Before You Send

Find out how your message’s subject line is likely to influence message performance. Test the performance of a single message or
compare up to 10 subject lines.
Einstein evaluates the subject lines as they appear in your subscriber’s inbox, and tests the subject line for potential bias.
Interpreting Test Results

276
Marketing Cloud Einstein and Analytics Einstein Copy Insights

To help you understand how the predicted performance compares to your own past performance in a business unit, contextual analytics
appear.
1. On the Einstein Copy Insights dashboard, enter a subject line with up to 80 characters in the Performance Tester input field.
2. Click Test.
The Einstein performance prediction and contextual analytics appear, indicating a predicted engagement rate range, most likely
engagement rate, and past performance.
3. To see a new prediction, modify the subject line and click Test.
Contextual analytics appear to help you understand how the predicted performance compares to your own past performance within
a business unit.

Graphic Indicator Engagement Rate Factor Description

Purple dotted line Average Engagement Rate Unweighted 90-day average engagement
rate (engagement rate mean) of all
commercial sends to at least 30 recipients
in your business unit

Amber shaded area Predicted Engagement Rate Range Distribution of possible engagement rates
based on your past sends, global data, and
the Einstein model’s confidence for your
enterprise (EID)

Amber dotted line Predicted Engagement Rate Predicted most likely engagement rate

Blue lines Other subject lines and subject line groups Performance distribution for subject lines
or subject lines groups from the past 90
days

After the contextual analytics, the most impactful language factors appear and show how much they influence the prediction. Use
these factors to adjust your subject lines.

Important: Predicted performance factors and guidance are unique for each subject line that you test. Don't generalize the
guidance or use it as a standard for best practices.
These factors are used to measure subject line performance. We show the top five most impactful factors for each tested subject
line.
• Number of numeric symbols
• Number of emoji symbols
• Ratio of uppercase characters
• How unique and original the subject line is
• Number of question marks
• Number of exclamation marks
• Number of dollar symbols
• Number of percentage symbols
• Number of time-sensitive words and phrases
• The degree of personalization
• Word count

277
Marketing Cloud Einstein and Analytics Einstein Content Selection

• Character length
• Contains specific keywords

Einstein Content Selection

Einstein Content Selection is a no-code, open-time experimentation tool for personalized content. Because Einstein selects content at
open time, it continues to evaluate for winning content while also experimenting to ensure that click-through rates are optimized.

Tip: Einstein can replace the need for segmenting sends or writing personalization into AMPscript by matching asset attributes
to consumer profile information.
Before starting, here are a few key concepts to note.
• Asset catalog—Use the set of images in a catalog in your experiments.
• Asset class—To determine how the images are used, add assets to an asset class. Asset classes are frequently used to determine
email template placement, such as the banner, main call to action, or the footer.
• Asset attribute—Categorize your images, personalize your content, and analyze click-through rates using attribute values. For
example, an asset attribute called Loyalty_Level has three values: Silver, Gold, and Platinum. When you pair the attribute with
consumer profiles, Einstein can match the correct set of experimental images using the customer’s loyalty level.
• Selection rule—Set up business rules to align Einstein with your business goals and intentions, such as how frequently content
can be reused.

Tip: In Setup, turn on Content Tagging for Einstein Content Selection to let Einstein automatically tag your images. Einstein
Content Tags provide another level of classification for you to identify the best content and whether you have enough content.
Use Case Examples
A marketer for an apparel company uploads a group of product image assets each week. Each product image asset features an item
that’s on sale that week. The marketer creates an asset class called WeeklySalesAssets and assigns the product image assets to it. The
marketer uses StartDate and EndDate to make sure that the latest weekly sale item is shown at open time.

Note: To further personalize the product images that appear, the marketer can add asset attributes that identify the sport associated
with the apparel. If the subscriber’s primary sport is available in their profile information, Einstein Content Selection can show
product images on sale that correspond to the customer’s interests.
A national grocery store chain decides to use email marketing to distribute weekly coupons. The marketers create an asset class called
CouponFeature. Each week, marketers upload image assets for the coupon products. Each image includes the CouponFeature asset
class. The marketing team uses StartDate and EndDate to ensure that the assets are available for selection in emails only during the week
that they’re on sale. The marketers also check Einstein Content Selection analytics to find the week’s highest performing assets. They’ve
enabled Einstein Content Tagging to monitor top-performing sale types and discovered that coupons for cleaning products outperformed
others. Then they compare the results with sales figures to understand the relationship between the items that customers click and the
items that they buy.
Getting Started
Configure a few settings, and supply Einstein with content assets. Import bulk image assets using one of these methods.
• Import an asset catalog file on page 281 that contains metadata and image links that you use in marketing content.
• Use the Einstein Content Selection API.
• Import images from Content Builder or directly from your desktop.

Tip: To keep your content fresh, use the API to import images each time a new image is added to your website or product catalog.

278
Marketing Cloud Einstein and Analytics Einstein Content Selection

Begin sending by adding an Einstein Content Block to an email. Einstein then optimizes asset selection for the highest click-through rate
at open time. If you decide to add customer profile information, each email is further customized for the subscriber using the assets that
you provide. You can also add content selection and fatigue business rules to help Einstein align with your business goals.

Note: Some email client providers’ security updates can cause an email open without user engagement. So if users opt into the
security updates that open email after a winning asset is selected, they could have already received an experimental asset.
As subscribers engage with your messages, Einstein analyzes click results to find out which assets spark interest in customers. Using
real-time analysis, Einstein finds the assets that prompt customers to click a link in the email. As analysis proves that an asset continually
contributes to increased click rates, Einstein selects that asset more frequently when customers open their email.

Note: Einstein Content Selection consumes super messages in Pro, Corporate, and Enterprise editions. Contact your account
executive for more information.

Related Content

Einstein Content Selection

• Evolve Your Marketing Strategy with Artificial intelligence

• Einstein Content Selection Basics
• Video: Getting Started with Einstein Content Selection - Einstein Content Selection Overview
• Video: Getting Started with Einstein Content Selection - Asset Pool Basics and Content Performance Testing
• Video: Getting Started with Einstein Content Selection - Fallback Asset and Fatigue Rules
• Video: Getting Started with Einstein Content Selection - Attribute Mapping, Exclusion Rules, and Variety Rules

24

Set Up Einstein Content Selection

Enable the Einstein Content Selection message block so you can add it to your messages in Content Builder.
Create and Upload an Asset Catalog File
Give Einstein the images that can be selected as content assets in your messages. Provide an asset catalog .csv file that contains a
URL and metadata for each content asset image file that Einstein can select. We provide a template to guide you. You can use Einstein
Content Selection in your email messages after uploading assets.
Manage Einstein Content Selection Assets
Manage the asset pool you created on the Asset Pool page after you add assets to Einstein Content Selection. You can add assets
to the pool in several ways. Upload an asset catalog file, upload a file from your desktop, import the asset from Content Builder, or
add the asset through an API The assets available to you are the image assets that Einstein Content Selection chooses from based
on the asset class of the content block. If you’re importing profile information, the selection is based on how the image attributes
align with the subscriber profile attributes.
Manage Asset Classes
You can add, modify, archive, and restore asset classes.

24
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

279
Marketing Cloud Einstein and Analytics Einstein Content Selection

Sync Your Consumer Profile Data Extension

If your organization has consumer or customer profile data that you want Einstein Content Selection to use when making selections,
sync the sendable data extension that contains your customer profile data. When the data extension gets updated, sync it again so
Einstein has the latest profile data. Or set up automatic daily profile syncing so you don’t have to.
Set Up Content Selection Rules
If you want Einstein Content Selection to observe rules about what content to select, set content selection rules. A content selection
rule governs when some assets can and can’t be selected and included in a message.
Set Fallback Assets
Choose an image asset that Einstein Content Selection displays when a matching asset can’t be found. Pick an image for each asset
class in your asset catalog file. Even if your fallback assets are unavailable, Einstein Content Selection selects an image if possible.
Change or Remove a Fallback Asset
If Einstein Content Selection can’t find an asset that matches your content selection rules, it displays a fallback image. You can change
or remove the fallback image for each asset class.
Find Out Why an Asset Was Selected
Search by subscriber key to review the details of an asset that was selected because of its likelihood to engage a specific subscriber.
Find out why Einstein Content Selection didn’t select other assets.
Einstein Content Selection Performance Analytics
Discover which aspects of your content images resonate with your audience. View performance over time by asset class, by asset
attributes including Einstein’s tag and tone attributes, or by job. You can also get details about assets that Einstein doesn’t select.
Einstein Content Selection Asset Distribution
Import more assets and keep an eye on your asset inventory’s status. Find an overview of assets and their distribution. Monitor how
many assets are active or expired, and how many assets expire soon.
Daily Selection and Click Events Report
The daily events report is a summary of subscriber content selection and click events. Use the report in Einstein Content Selection
to track subscriber views and engagement. Reports are retained for 90 days.
Use Local Weather Conditions to Target Assets
You can target assets based on the weather forecast and conditions for a subscriber’s location. For example, you can promote
sunscreen when the UV Index is high or promote raincoats when there’s a 75% chance of rain in the next 5 days.
Einstein Content Selection and Testing Model Card
The model in this card analyzes message content performance to optimize email engagement.

Set Up Einstein Content Selection

Enable the Einstein Content Selection message block so you can add it to your messages in Content Builder.
Before you can use Einstein Content Selection in your messaging, activate the feature in Setup and make it available in all your business
units. Upload an asset catalog file that lists the assets that Einstein can use, including each content asset's URL and metadata. Provide a
contingency image for cases when your assets or fallback images aren't selectable. To make content selection more sophisticated, you
can sync your consumer profile information and set selection rules and fallback images.
1. In Marketing Cloud Setup, click Einstein.
2. Click Einstein Content Selection.
3. Click Activate.
4. From the dropdown, select how subscribers are identified, either Subscriber Key or Subscriber ID.

280
Marketing Cloud Einstein and Analytics Einstein Content Selection

If necessary, check with the technical marketer or data architect who set up your consumer profile data extension whether to use
Subscriber Key or Subscriber ID.

5. To use conversion tracking, select Track ECS Links.

This setting enables links from Einstein Content Selection blocks to pass tracking parameters to a landing page. For more information,
see Conversion Tracking.

6. Select an archiving setting for assets.

7. To automatically tag your assets, click Activate, and turn on Einstein Content Tagging.
Einstein Content Tagging tags your images for a deeper classification level. You can see these tags in Performance Analytics as an
asset attribute to help identify which types of content work best and whether you have enough content.
To help Einstein determine which tags to use, set a minimum confidence level and maximum number of tags to apply.

Note: When you turn off automated tagging, tags that Einstein has applied are deleted.

8. To upload an image that appears when your assets aren’t available and no fallback images exist, click Upload Image.
9. Add the URL that users are directed to when they click your contingency image in a message.
To use the weather feature in Einstein Content Selection, choose the temperature unit, Celsius, or Fahrenheit, to configure
temperature-based targeting in the business unit. You must set up a profile sync to detect weather for individual subscribers. You can
set up sync at any time. It doesn’t prevent you from configuring your assets to support weather targeting. After you enable the weather
feature, configure asset classes on page 285 to be weather-enabled.

SEE ALSO:
Einstein Content Tagging Confidence Level

Create and Upload an Asset Catalog File

Give Einstein the images that can be selected as content assets in your messages. Provide an asset catalog .csv file that contains a URL
and metadata for each content asset image file that Einstein can select. We provide a template to guide you. You can use Einstein Content
Selection in your email messages after uploading assets.
Download an asset catalog file template. Create an asset catalog file that consists of the required fields in this template and more fields
that could help you differentiate assets.
The asset catalog file must include these columns.
AssetName
A unique identifier for the asset. Must be a text string.
AssetClass
A group or set of assets that can be selected and displayed interchangeably in a message content block. Asset classes are used to
group related images that are commonly used in marketing messages. See the examples on this page. You define each asset class
by naming it. Create as many or as few asset classes as you need.
ImageURL
An internet-accessible URL where a content asset image is stored.
LinkURL
The URL that you want customers to go to when they click the content asset image in your message.
Available
A “Y” (yes) value tells Einstein that the content asset image is available for selection. An “N” (no) value means that the content is
unavailable for selection. Y and N are the only valid values for this field.

281
Marketing Cloud Einstein and Analytics Einstein Content Selection

StartDate
The date after which the asset is eligible to be selected in YYYY-MM-DD format. This value is interpreted to be in GMT. If you don’t
specify a start date, the start date is set to the current day, and the asset is eligible for selection immediately.
EndDate
The date after which the asset is no longer eligible to be selected in YYY-MM-DD format. This value is interpreted to be in GMT. If
you don’t specify an end date, the asset is eligible for selection indefinitely.
Fallback
A “Y” (yes) value tells Einstein to use this asset as a fallback image when Einstein can’t select an image in a given asset class. An “N”
(no) value tells Einstein not to use this image as a fallback image. Y and N are the only valid values for this field.
You can add fields to describe your asset image to help the algorithm perform better when selecting a personalized asset. Examples
include ProductCategory, Language, Country, or Affinity. Adding these fields creates asset attributes for the image. To use multiple values
in an attribute in a bulk asset upload, use a tilde separator in your .csv file. For instance, for the Affinity attribute, Hiking~Camping indicates
that the image asset applies to both.
Use asset classes to categorize marketing asset images according to how the images are used in your messages. For example, placement
in an email template can be in the banner, the main call to action, the secondary call to action, or the footer.

Tip: Choose attributes that aid Einstein in selecting assets for your customers specifically. For instance, if your customers are
patients in a large public health system, using an extra field, such as PreferredLocation, helps Einstein select image assets that
pertain only to the hospital or clinic that each subscriber chooses during enrollment.
1. If you’ve never before uploaded an asset catalog file, click Upload File. If you’ve already uploaded an asset catalog file, continue to
step 2.
2. If you’re importing assets to add to your asset pool, or to update assets already in the asset pool, click New Asset.
3. Click Import Assets.
4. Select your asset catalog file.
When the asset file upload is complete, a confirmation message appears and more settings are available. You can start using Einstein
Content Selection in content blocks when your asset catalog file upload is complete.

Example: Asset Classes

Use asset classes to categorize marketing asset images according to how the images are used in your messages.
A marketer for a college builds promotional emails for the admissions department. In each email, the institution highlights its
upcoming recruiting events. At any time, there are four or five upcoming events. So the marketer creates an asset class called
Events for assets that contain information about the college’s upcoming recruiting activities.
A marketer for an apparel company uploads a group of product image assets each week. Each product image asset features an
item that’s on sale that week. The marketer creates an asset class called WeeklySalesAssets and assigns the product image assets
to it. The marketer uses StartDate and EndDate to make sure that the latest weekly sale item is shown at open time.
A national grocery store chain decides to use email marketing to distribute weekly coupons. The marketers create an asset class
called CouponFeature. Each week, marketers upload image assets for the coupon products. Each image includes the CouponFeature
asset class. The marketing team uses StartDate and EndDate to ensure the assets are only available for selection in emails during
the week they’re on sale. The marketers also check Einstein Content Selection analytics to find the week’s highest performing
assets. They’ve enabled Einstein Content Tagging, so the marketers also look for top performing sale types and discover that
coupons for cleaning products outperform others. Then they compare the results with sales figures to understand the relationship
between items customers click and items they buy.
Additional Fields
Marketers can use additional fields in a variety of ways.

282
Marketing Cloud Einstein and Analytics Einstein Content Selection

• To use Einstein Content Selection’s performance analytics for click-through rates by product, a marketer can create an asset
attribute field in the asset catalog called ProductCategory. The field indicates the primary product type the asset image shows.
• To reduce segmentation requirements by language, an additional field called Language could specify the language that text
in the asset appears in.
• To target the most relevant content without managing multiple audiences and sends, a marketer can create an additional
field for the asset location and name it Country or Locale.
• To show content based on a user’s local weather forecast.

Manage Einstein Content Selection Assets

Manage the asset pool you created on the Asset Pool page after you add assets to Einstein Content Selection. You can add assets to the
pool in several ways. Upload an asset catalog file, upload a file from your desktop, import the asset from Content Builder, or add the
asset through an API The assets available to you are the image assets that Einstein Content Selection chooses from based on the asset
class of the content block. If you’re importing profile information, the selection is based on how the image attributes align with the
subscriber profile attributes.

Tip: To make batch changes to your assets, export them in a .csv file, modify the assets, and then import the file. You don’t have
to include all asset attributes with each update. Include only the values that you’re changing.
Enable an asset to make it available so Einstein Content Selection can select it for a message. Disable an asset when you don’t want
Einstein Content Selection to select it.

Tip: To control availability you can also use start and end dates.

1. To access the asset pool in Einstein Content Selection Settings, click View All Assets.
2. To create a single asset, import multiple assets, or view file import status, click New Asset.
a. To create a single asset, click New Asset again.
b. To upload an asset catalog .csv file, click Import Assets.
c. To check the file import progress and success or failure status, click View File Imports.
d. To export your assets into a .csv file, click Export Assets.

3. To change an asset’s metadata, click Edit.

4. To view an asset, click its thumbnail image.

Add an Asset
Upload an asset catalog file or use the Einstein Content Selection API to quickly add multiple assets at once. You can also add a single
asset. For improved reliability, image size is limited to 2 MB when using the CSV catalog import option or the API. Images added
through in the application are still limited to 1 MB.
Add an Asset Attribute
Help Einstein make the best, most context-rich selections by adding attributes to your assets. An attribute is metadata about an
asset that helps Einstein categorize it, making selections smarter when paired with subscriber profile information.
Edit Asset Attributes
Update asset attributes so that Einstein’s selection incorporates current, relevant metadata. You can add, edit, or delete attribute
values.
Archive an Asset
When an image asset isn’t available for use, archive it.

283
Marketing Cloud Einstein and Analytics Einstein Content Selection

Add an Asset
Upload an asset catalog file or use the Einstein Content Selection API to quickly add multiple assets at once. You can also add a single
asset. For improved reliability, image size is limited to 2 MB when using the CSV catalog import option or the API. Images added through
in the application are still limited to 1 MB.
1. Click New Asset.
2. Complete the standard fields and availability settings.

Note: AMPscript isn’t accepted in an asset’s destination URL, but you can add personalized parameters using Parameter
Manager. The parameters set up in Parameter Manager are appended to your destination URL. If you can’t use Parameter
Manager, see Salesforce Stack Exchange for options.

3. Complete the additional fields.

The additional fields that appear when you create a single asset are the same additional fields included in the initial asset file.

4. If your org uses Einstein Content Tagging, deselect the automatically generated tags that you don’t want to apply.
5. Save the asset.

Add an Asset Attribute

Help Einstein make the best, most context-rich selections by adding attributes to your assets. An attribute is metadata about an asset
that helps Einstein categorize it, making selections smarter when paired with subscriber profile information.
1. In Einstein Content Selection Settings, in the Configure Asset Attributes section, click Edit.
2. Click New Attribute.
3. Name the attribute, and provide attribute values.
When you select Allow multiple values from a specified list, you can supply the values in the text field that appears.

4. If you’re using the weather feature, click Weather Attribute and choose an attribute type.
If you don’t see the weather attributes, make sure that the weather feature is activated in Setup and that weather attributes are
enabled in the asset class.
• Temperature—Name the value, such as Hot or Chilly, and define its temperature range.
• Precipitation—Choose the precipitation type, such as Rain or Snow, and define the probability of occurrence.
• Indices—Choose an index, and define the value of the index. For example, the UV Index is High, or the Air Quality is Good.
• Alarms—Allows you to select an alarm type for each weather asset. For example, Rain or Snow.
Weather forecasts use the AccuWeather API. For index and alarm threshold information, see the AccuWeather Daily Index Categories
and Level Values and the Weather Alarm Thresholds.

5. Save your work.

Tip: If you expect to add images daily or weekly, reduce manual work by using the Einstein Content Selection API. Also consider
integrating with your website. Then when you add images to your website, they’re also added to the asset pool.

Edit Asset Attributes

Update asset attributes so that Einstein’s selection incorporates current, relevant metadata. You can add, edit, or delete attribute values.

Note: You can also edit asset attributes by using the Einstein Content Selection API or the Asset Catalog on page 281.

1. In Einstein Content Selection Settings, in the Configure Asset Attributes section, click Edit.

284
Marketing Cloud Einstein and Analytics Einstein Content Selection

2. Click next to the asset attribute that you want to edit.

You can’t edit the name of an attribute that’s in use.
When you select Allow multiple values from a specified list, you can supply the values in the text field that appears.

3. Name the attribute, and provide attribute values if necessary.

4. Save your work.

Archive an Asset
When an image asset isn’t available for use, archive it.
1. Navigate to your organization's assets by clicking View All Assets.
2. Find the asset to archive.
3. Click .
4. Click Archive.

Manage Asset Classes

You can add, modify, archive, and restore asset classes.
1. In Einstein Content Selection Settings, in the Configure Asset Classes section, click Edit.
2. To create an asset class, click New Asset Class, and name and describe the asset class.

Tip: Create an asset class instead of renaming an existing asset class. Move the assets to the new class, then archive the defunct
asset class.

3. If targeting by weather in the asset class and you have Weather enabled for Einstein Content Selection in Setup, follow these steps.
a. Configure the asset class to be weather-enabled. You can then apply a set of weather-specific asset attributes to the assets in
the class.
b. Choose the behavior to use when a subscriber’s location isn’t available.

Note: If you select Show only assets without weather attribute values and configure a weather-enabled asset class,
you need enough assets without weather attributes in case profile information doesn't include the appropriate location
information. If you’re using weather only as an additional attribute to refine targeting but isn’t exclusionary, we recommend
selecting Show assets with any weather attribute values.

c. Choose the forecast period.

Note: When forecasted weather includes multiple days, an occurrence on any of the days triggers a selection. If multiple
conditions apply during a forecast period, assets with either matching asset attribute apply. When you want to forecast
over multiple days and select assets based on a single condition, create an asset attribute for the matching condition only,
select Show only assets without any weather attribute values. Then, provide several assets without any weather
attribute values defined.

4.
To edit, archive, or restore an asset class, click next to the asset class.
a. Select Archived Asset Classes.
b. Click next to the asset class to restore.

285
Marketing Cloud Einstein and Analytics Einstein Content Selection

c. Click Restore.

Note: When you archive asset classes, all fallback image designations are automatically removed and archived.

SEE ALSO:
Einstein Content Selection

Sync Your Consumer Profile Data Extension

If your organization has consumer or customer profile data that you want Einstein Content Selection to use when making selections,
sync the sendable data extension that contains your customer profile data. When the data extension gets updated, sync it again so
Einstein has the latest profile data. Or set up automatic daily profile syncing so you don’t have to.
To access this setting, first upload an asset catalog file.
Consumer profile data attributes are attributes that marketers use to differentiate customers into segments, such as primary product
category of interest, favorite brand-related activity, country of residence, or language.

Note: Data Extensions stored in the Shared Data Extension Folder can’t be selected as a Consumer Profile Data Extension for a
child business unit. Only the parent business unit can access Data Extensions stored in the Shared Data Extension Folder for Sync.
1. In Einstein Content Selection Settings, click Sync Data Extension.
2. Select the sendable data extension that includes your customer profile data.
The field length limit is 100 characters.

3. To enable Einstein Content Selection to sync this data extension on a daily schedule, select Recurring sync.
a. Set a schedule, including the time of day your profile data extension sync runs.

4. Click Save.
When the sync completes, its status appears on the Settings page.

Important: When the data extension you selected is updated, repeat this process so Einstein Content Selection can access the
latest consumer profile information.

Identify Attributes That Can Introduce Bias

To help you ensure that your customer profile attributes don’t facilitate intentional or unintentional bias, Einstein Content Selection
scans and flags English language profile attributes that can introduce bias. Einstein scans attribute names and attribute values, then
notifies you that an attribute you created can introduce bias so that you can decide whether to include, edit, or exclude the attribute.
Add or Edit Profile Attributes
You can add and edit attribute values.

Identify Attributes That Can Introduce Bias

To help you ensure that your customer profile attributes don’t facilitate intentional or unintentional bias, Einstein Content Selection
scans and flags English language profile attributes that can introduce bias. Einstein scans attribute names and attribute values, then
notifies you that an attribute you created can introduce bias so that you can decide whether to include, edit, or exclude the attribute.
Salesforce defines bias as using a person's immutable traits to classify them or market to them. Because Einstein bases its selections on
the profile attributes that you create, it’s essential that the attributes you create don’t permit or enable harmful bias.

286
Marketing Cloud Einstein and Analytics Einstein Content Selection

To help you ensure that you don’t introduce bias, Einstein Content Selection flags an attribute if that attribute could intentionally or
unintentionally introduce bias when used. Attributes are flagged when the attribute itself as a category could contribute to bias or when
the attribute’s values could contribute to bias.

Example: A marketer creates an attribute called postal code. In the United States and other countries, postal codes have historically
been used for many purposes, including as an indicator of their residents’ race or financial status. For this reason, using a person’s
postal code as a factor in marketing to them can influence Einstein Content Selection selections unfairly. So postal code is flagged
as a potentially sensitive profile attribute.

When an attribute that you create is flagged, Einstein Content Selection still allows you to save and use the attribute. Salesforce customers
can use a flagged attribute as a way to ensure that they aren’t enabling conscious or unconscious bias. For this reason, the app flags
attributes so you can evaluate all the ways that they could be used, then make a responsible decision to keep or discard them.
A guideline that can promote responsible use of attributes is to focus your marketing on behavioral and preferential attributes, not just
demographic attributes such as age or gender. Examples of behavioral and preferential attributes include activity preferences and
favorited content.

Important: Einstein Content Selection evaluates the attribute names you supply, including synonyms, abbreviations, and formatting
in its analysis to detect possible bias. Attributes are scanned against a list of English language attribute names only.

Potentially Sensitive Attributes

The following attribute names are flagged, as are their synonyms, abbreviations, and the formatting consistent with their use in English.

Potentially Sensitive Attributes

First or Last Name

Sexual Orientation

Age

Gender or Gender Identity

Race

Postal Code

Nationality

Religion

Marital Status

Disability

Status as Recipient of Public Assistance

Criminal Convictions

Trade Union Memberships

287
Marketing Cloud Einstein and Analytics Einstein Content Selection

Potentially Sensitive Attributes

Medical Condition

Financial Status

Political Opinions

Philosophical Beliefs

Family Status, including pregnancy

Genetic Information

Citizenship Status

Add or Edit Profile Attributes

You can add and edit attribute values.
1. In Einstein Content Selection Settings, in the Configure Profile Attributes section, click Edit.
2. Click Manage Attributes.
3. Select the data extension that includes the profile attribute that you want to add.
4. Click Next.
5. Set the notification and sync settings, if necessary.

Tip: You can set the data extension to sync on a recurring schedule.

6. Click Next.
7. Select the attribute to add.
8. If weather is enabled, choose the location attributes for the profile.

Note:
• For a full list of supported countries, see Accuweather’s supported locations.
• Postal codes are fully supported in the United States, Canada, the United Kingdom, and Germany. We recommend you
use the city as a backup in countries where the postal codes are only partially supported. This includes Andorra, Argentina,
Australia, Austria, Belgium, Brazil, Bulgaria, Croatia, Czech Republic, Denmark, Finland, France, Guatemala, Hungary, India,
Italy, Luxembourg, Mexico, Moldova, Netherlands, New Zealand, Norway, Poland, Russia, Slovakia, Slovenia, Spain, Sweden,
Switzerland.
• Provide the location using either City and Postal Code, or Latitude and Longitude coordinates that are supported to the
100th decimal place.
• You can provide City, State, and Country names in a local language instead of its English equivalent For example, you use
the city name København instead of Copenhagen. When using a non-English location name, indicate the language by
providing a column in the profile data extension named Language and include the standardized ISO 639-1 language code.
In this example, the Language column includes the ISO code NL to indicate the correct language.

9. Click Next.
10. If necessary, edit the attribute’s values. To define one or more values for this attribute, click Add Value.
11. Save your work.

288
Marketing Cloud Einstein and Analytics Einstein Content Selection

Set Up Content Selection Rules

If you want Einstein Content Selection to observe rules about what content to select, set content selection rules. A content selection
rule governs when some assets can and can’t be selected and included in a message.
To access this setting, first upload an asset catalog file.
Find Content Selection Rules in Einstein Content Selection Settings. Content Selection Rules include the option to map attributes from
your asset catalog file to attributes in your customer profile data extension, set rules about when to exclude an asset, and set rules to
keep an asset from showing too often.
1. To get started, click Edit.

1. Map Asset Attributes to Consumer Attributes

To help Einstein make targeted selections, map asset catalog attributes to consumer attributes. If an asset class contains assets in
multiple languages, you can specify that only the assets that correspond to the subscriber’s language are available to select.
2. Set Fatigue Rules
Because assets that get clicks and generate engagement guide asset selection, Einstein Content Selection can select the same asset
for the same customer more than once. Configure fatigue rules to prevent a customer from seeing the same image more often than
you want them to.
3. Set Exclusion Rules
Exclusion rules are conditions that you set to tell Einstein Content Selection when not to select a particular type of asset for a subscriber.
4. Set a Variety Rule
Prevent Einstein from selecting the same asset image for an asset attribute more than once for a subscriber in a single message. By
setting a variety rule, you can tell Einstein to vary the assets displayed when you use an asset with the same attribute more than
once in a message. You can set one variety rule per business unit.

Map Asset Attributes to Consumer Attributes

To help Einstein make targeted selections, map asset catalog attributes to consumer attributes. If an asset class contains assets in multiple
languages, you can specify that only the assets that correspond to the subscriber’s language are available to select.
Ensure that each attribute you use in a Must Match rule can be populated for all subscriber profiles and that assets are available for each
possible value.
Guiding Einstein Content Selection using the Must Match option can prevent unintended selections. But using this option can limit the
number of available assets that Einstein Content Selection can select. When using Must Match rules, make sure that your account has
enough assets to select one for each subscriber.
When using a Must Match rule where an asset attribute value is null or contains an empty string and a corresponding profile attribute
is provided, the asset isn’t available to select because there’s a mismatch. If the asset’s value defined in a Must Match rule is omitted, it
matches only when the subscriber’s profile attribute is also omitted.
In instances where an asset is eligible only to a subset of subscribers but most assets are eligible for everyone, use Exclusion rules on
page 290 instead of Must Match rules. For example, use Exclusion rules if one subscriber subset is for people only over age 21. Using
Exclusion rules in this case avoids tagging the nonrestrictive assets with values that map to all age groups.

Tip: If an expected asset attribute doesn’t appear, check Configure Asset Attributes in Settings. If you imported assets as a batch,
check the asset catalog file to ensure that the attribute has a heading in the file’s first row and appears in a separate column.
1. Click a consumer attribute.
2. Select the attribute from your consumer profile data extension that relates to the asset attribute in the same row.
3. If the asset attribute value must be identical to the subscriber attribute value, select Must Match.

289
Marketing Cloud Einstein and Analytics Einstein Content Selection

If an asset class contains assets in multiple languages, use this setting to specify that only the assets that correspond to the subscriber’s
language are available to select. Match the CustomerLanguage asset attribute with the Language consumer profile attribute.
The Must Match option can prevent unintended selections, but it can limit the number of available assets that Einstein Content
Selection can select. When using Must Match rules, make sure that your account has enough assets to select one for each subscriber.

4. To use the Must Match rule when Einstein Content Selection must show a fallback asset, select Apply to Fallback.
The Apply to Fallback option limits the asset pool for your fallback image. To use this feature, make sure that you have a fallback
image for each attribute value and consider applying the image to one asset attribute. To access this feature, contact your Salesforce
account representative.

5. Repeat these steps for each asset attribute that you want to map.
6. Save the mapping.

Example: Northern Trail Outfitters (NTO), an outdoor adventure apparel company, uploads image assets for a promotion related
to the Olympic Games in its asset catalog file. Each image features the flag of the country where the promotion runs. NTO includes
another field in the asset catalog file called Country. To ensure that image assets with the correct country’s flag appear to subscribers
in that country, NTO maps the Country asset attribute to the CustomerCountry field in its consumer profile data extension. Then,
NTO selects Must Match to tell Einstein Content Selection to select only this asset when the subscriber’s country matches the
country in the asset attribute value. To manage subscribers who are missing their country profile data, NTO provides a few assets
where no value is provided for Country.

SEE ALSO:
Edit Asset Attributes

Set Fatigue Rules

Because assets that get clicks and generate engagement guide asset selection, Einstein Content Selection can select the same asset for
the same customer more than once. Configure fatigue rules to prevent a customer from seeing the same image more often than you
want them to.
The default Days After Last Selection, Days After Last Click, and Selection Maximum values appear when you open Einstein Content
Selection’s fatigue rules. You can change these values.
You can set fatigue rules for all asset classes. Or create a rule for only one asset class at a time.
1. To change the default settings for all asset classes per customer, click a dropdown list.
2. To set a rule for a single asset class, click Add Rule.
3. Select an asset class.
4. Choose a value for each dropdown next to the asset class you selected.
5. To create rules for another asset class, repeat these steps.
6. Save the rules and settings you created.

Set Exclusion Rules

Exclusion rules are conditions that you set to tell Einstein Content Selection when not to select a particular type of asset for a subscriber.
1. Click Add Rule.
2. Select the asset attribute that contains the value that you want to exclude.
3. Select the value that you want to exclude.

290
Marketing Cloud Einstein and Analytics Einstein Content Selection

4. Select the consumer attribute that you want to exclude.

5. Select the consumer value that you want to exclude.
6. To add rules, repeat these steps.
7. Click Save.

Example: Northern Trail Outfitters (NTO), an outdoor adventure apparel company, includes an image asset that shows a coupon
offer in its asset catalog file. But NTO’s marketers don’t want to show a coupon offer to a premium customer who has consistently
made large purchases, so NTO creates this exclusion rule.
Don’t show assets when:
Asset Attribute = ImageClass, and Asset Value = Coupon AND
Consumer Attribute = LoyaltyLevel, and Consumer Value = Premium
This rule keeps Einstein Content Selection from showing the coupon asset when a customer’s LoyaltyLevel attribute’s value is
Premium.
Example 2
NTO sells an energy drink that it promotes only to adult customers. NTO has a customer profile attribute to indicate whether a
customer is 21 years of age or older. When the customer’s age isn’t known, NTO defaults the profile attribute to under 21 to ensure
compliance. NTO creates this exclusion rule.
Don’t show assets when:
Asset Attribute = AgeRestricted, and Asset Value = True AND
Consumer Attribute = 21andOver, and Consumer Value = False
This rule keeps Einstein Content Selection from showing the energy drink asset to customers who are under the age of 21 or whose
age is unknown.

Set a Variety Rule

Prevent Einstein from selecting the same asset image for an asset attribute more than once for a subscriber in a single message. By
setting a variety rule, you can tell Einstein to vary the assets displayed when you use an asset with the same attribute more than once
in a message. You can set one variety rule per business unit.
1. Click Variety.
2. Select an asset attribute.
3. Save.
Selections that include this attribute vary.

Set Fallback Assets

Choose an image asset that Einstein Content Selection displays when a matching asset can’t be found. Pick an image for each asset class
in your asset catalog file. Even if your fallback assets are unavailable, Einstein Content Selection selects an image if possible.
Einstein Content Selection displays a fallback asset when an asset that matches your content selection rules can’t be found. For example,
a fallback asset is selected when every asset in an asset class has expired.
• When a fallback asset can’t be selected, Einstein Content Selection attempts to select a content asset that fatigue rules would
otherwise disallow.
• When no asset is available even after fatigue rules are bypassed, Einstein Content Selection selects your contingency image.

291
Marketing Cloud Einstein and Analytics Einstein Content Selection

A card appears for each asset class that Einstein Content Selection finds in the asset catalog file. You can select any asset that is available
for each asset class.
1. Click Select Asset in a blank card.
2. Select an asset.
3. Save the fallback asset selection.
4. Save the fallback assets you selected.

Change or Remove a Fallback Asset

If Einstein Content Selection can’t find an asset that matches your content selection rules, it displays a fallback image. You can change
or remove the fallback image for each asset class.
1. In Settings, select Fallback Assets.
2. Select an asset class.
3. To use a different fallback asset, select a new asset.
4. To remove a fallback asset and use a contingency image instead, select Clear All.

Find Out Why an Asset Was Selected

Search by subscriber key to review the details of an asset that was selected because of its likelihood to engage a specific subscriber. Find
out why Einstein Content Selection didn’t select other assets.
Use this page to view information about a subscriber and the assets Einstein selected for them. View the subscriber’s profile attributes,
the email send jobs that sent messages to the subscriber, and the assets that Einstein selected. If an email open event isn’t recorded for
a subscriber, email send jobs sent to the subscriber are listed, but no assets appear.

Note: Some email client providers’ security updates can result in an email open without user engagement.

Profile attributes are shown in their current state. Profile attributes can change after Einstein selects an asset.
1. Click View Selections in Performance Analytics.
2. Add a subscriber key and search.
A list of emails sent to the subscriber that include the Einstein Content Selection content block appears.
3. Select a send to view the assets evaluated for that subscriber for that send.
4. Click an asset’s link for details, including which assets were ineligible for selection and why.
a. To see its attributes and performance in the Asset Details pane, select an asset.

Note: Clicks refer to the most recent time the subscriber clicked or tapped the asset image, not the other links within the
message.

b. To see the selection and exclusion rules that were configured to guide Einstein’s selections in your account, click Selection
Rules on the Selection Details page.

Note: Assets display their current value and can change after selection time.

292
Marketing Cloud Einstein and Analytics Einstein Content Selection

Einstein Content Selection Performance Analytics

Discover which aspects of your content images resonate with your audience. View performance over time by asset class, by asset
attributes including Einstein’s tag and tone attributes, or by job. You can also get details about assets that Einstein doesn’t select.
To access Einstein Content Selection’s performance analytics data, go to Einstein, and click Einstein Content Selection. If you use the
Einstein Content Selection content block in your messages, selection analytics appear when you click Performance Analytics.
Use Einstein Content Selection’s analytics to understand which assets are the most and least successful and to review details about
selected assets, including which aspects attract clicks. You can look at how assets in an asset class perform across more than one email
send, or how a content block in a particular email is doing. To understand which assets and asset values associated with an asset attribute
perform well, sort by asset attribute.
You can select an asset class to view performance for all its assets. To see performance by job ID, search for a particular job by its ID, then
select the block in the job that you’re interested in.
Pick an asset attribute to see performance for assets with the selected attribute. To find out which aspects of your content assets are
getting clicks, select the Tags asset attribute. You can search for and filter by specific tags.

Tip: Einstein uses AI to analyze and tag the image files according to what’s in the image. You can correlate the tag values for
aspects or features of the image that are identified by Einstein’s tags with selections and clicks. This correlation shows you which
aspects of your content are meaningful to your audience.
When the page appears, top-performing assets are sorted by click-to-open ratio (CTOR) by default. If an email open event isn’t recorded
for a subscriber, then email send jobs sent to the subscriber are listed, but no assets appear.

Note: Some email client providers’ security updates can result in an email open without user engagement.

Use daily reports to get subscriber-level details on selections and click-throughs.

Tip: If you have additional feature requests related to analytics or automated access to Einstein Content Selection data, share your
use case and request by submitting feedback on the Idea Exchange.

View Subscriber Content Selections

View a history of subscriber sends and why a subscriber received certain image selections.

View Subscriber Content Selections

View a history of subscriber sends and why a subscriber received certain image selections.
1. On the Einstein Content Selection page, click the Performance Analytics tab.
2. Click View Selections.
3. To view the subscriber details, enter the subscriber key in the search box.
4. To see the other images that were selectable at the time and asset details, click the asset name. The asset details show the current
settings for the asset. To see details when the asset was selected, expand the asset. Values that are different have an asterisk.

Einstein Content Selection Asset Distribution

Import more assets and keep an eye on your asset inventory’s status. Find an overview of assets and their distribution. Monitor how
many assets are active or expired, and how many assets expire soon.
To access Einstein Content Selection’s asset distribution data, go to Einstein and click Einstein Content Selection. If you use the Einstein
Content Selection content block in your messages, access distribution analytics by clicking Asset Distribution.
Filter by asset class and by attribute to see which assets are available, active, and expiring or expired.

293
Marketing Cloud Einstein and Analytics Einstein Content Selection

Tip: Einstein uses AI to analyze and tag the image files according to what’s in the image. Select Tags as the Asset Attribute to see
how images that Einstein tagged are performing.

Daily Selection and Click Events Report

The daily events report is a summary of subscriber content selection and click events. Use the report in Einstein Content Selection to
track subscriber views and engagement. Reports are retained for 90 days.
Performance Analytics that you see on the Einstein Content Selection page are based on the timezone settings for Marketing Cloud. The
daily subscriber report data is based on the UTC timezone. Daily counts can differ between the two. The daily subscriber report usually
is available at about 03:00 UTC.
To access the reports, click Daily Reports in Performance Analytics in Einstein Content Selection. Then download a zipped CSV file of the
report.

Note: You can access this report via API to get this report on other platforms. See the Einstein REST API for developer information.

Table 10: Report Format

Field Name Description
channel The channel where the asset’s event occurred. Only email is supported.

ImageURL URL for the hosted image

timestamp Timestamp for the event. For example, 1970-01-30T18:40:47.000Z

AssetName Name of the asset

StartDate The start date defined for the asset. This setting defines the date the asset is available
for selection.

LinkURL The destination URL for the asset.

subscriber_id Hashed value for the Subscriber ID or Subscriber Key, depending on the profile
identifier provided in Setup. For more information, see Setup Einstein Content Selection
on page 280.

job_id The job identifier for the send.

selected_as_fallback Identifies whether the asset is available to the subscriber as a fallback as TRUE or
FALSE. For more information, see Set Fallback Assets on page 291.

EndDate The end date defined for the asset. This setting defines the last day that the asset is
available for selection.

event_type Selection or click event.

AssetClass Defines the asset class that the asset is assigned to.

event_date The date of the selection or click event in YYYY-MM-DD format.

294
Marketing Cloud Einstein and Analytics Einstein Content Selection

Use Local Weather Conditions to Target Assets

You can target assets based on the weather forecast and conditions for a subscriber’s location. For example, you can promote sunscreen
when the UV Index is high or promote raincoats when there’s a 75% chance of rain in the next 5 days.
To use targeted weather, the profile attributes must include location information, such as city, postal code, state, country, or latitude
and longitude. Learn more about supported location information in Manage Profile Attributes on page 288.
Add weather condition attributes to the asset on page 284 in one of four ways.
• Use temperature ranges to differentiate hot versus cold days using the forecasted daytime high.
• Use precipitation ranges to define a chance of any type of precipitation. Or define a precipitation range for a specific type of
precipitation, including rain, snow, ice, and thunderstorms.
• Use indices to determine appropriate activities given the forecast. For example, UV Index is High, or Air Quality is Good.
• Set alarms to trigger when a weather condition meets or exceeds a threshold.
The weather service uses the subscriber location information provided in the customer profile data extension to look up forecasted
weather conditions and uses metadata on the image asset for targeting purposes. See Sync Your Customer Profile Data Extension on
page 286 for more information.
For each asset class, use configuration options to manage the forecast period and how to target subscribers when weather conditions
can’t be retrieved for the subscriber. See Manage Asset Classes on page 285 for more information.

Disable or Pause the Einstein Content Selection Weather Feature

Disabling the weather feature permanently removes all weather-related metadata. If you don’t want to lose your weather-related
metadata, you can pause the feature.
Get Started with Weather to Target Assets
Before you can use local weather forecasts and conditions to target assets, complete these setup items.

SEE ALSO:
Accuweather API
Weather Alarm Thresholds

Disable or Pause the Einstein Content Selection Weather Feature

Disabling the weather feature permanently removes all weather-related metadata. If you don’t want to lose your weather-related
metadata, you can pause the feature.
To disable the weather feature, in Setup, click Deactivate & Delete.
To pause the feature, deselect Weather Enabled on each asset class. No data is deleted, and you can turn on the weather feature at
any time without losing data.

Get Started with Weather to Target Assets

Before you can use local weather forecasts and conditions to target assets, complete these setup items.
1. Enable the Weather option in Setup > Einstein >Einstein Content Selection. See Set Up Einstein Content Selection on page 280 for
more information.
An admin must activate weather in Setup. After it’s activated, you can choose the temperature unit to use to configure
temperature-based targeting in the business unit.

2. Sync customer profiles on page 286 with location information.

295
Marketing Cloud Einstein and Analytics Einstein Content Selection

3. Identify appropriate Asset Classes as Weather Enabled to show the appropriate asset options. See Manage Asset Classes on page
285 for more information.
4. Create weather-related asset attributes on page 284 in the asset class.
5. Add weather attribute values on page 284 to assets.
Now, you can target assets based on the weather forecast on page 295 and conditions for a subscriber’s location. You can disable the
weather feature permanently at any time. This action removes all weather-related metadata. If you don’t want to lose your weather-related
metadata, you can pause the feature instead. See Disable or Pause the Einstein Content Selection Weather Feature on page 295 for more
information.

Einstein Content Selection and Testing Model Card

The model in this card analyzes message content performance to optimize email engagement.

Model Details
The Marketing Cloud Einstein Content Selection and Testing model optimizes customer engagement with email content using these
training algorithms, parameters, fairness constraints, and features.
Intended Use
The Marketing Cloud Einstein Content Selection and Testing model is intended for these use cases.
Relevant Factors
These factors are associated with the Marketing Cloud Einstein Content Selection and Testing model.
Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance
measures are associated with the Marketing Cloud Einstein Content Selection and Testing model. Customers are responsible for
monitoring the accuracy of Einstein Content Selection.
Training Data
You have a customized version of the model that’s trained on your data alone. Data from one Salesforce customer doesn’t affect the
behavior for another Salesforce customer. While model training happens for each customer on their data, the initial development
of the model is validated with a representative set of pilot customers’ data.
Ethical Considerations
Review the ethical factors associated with the Marketing Cloud Einstein Content Selection and Testing model. To avoid bias and
other ethical risks, the Einstein Content Selection and Testing model doesn’t include demographic data. Further bias is mitigated by
training the model with a robust content catalog.

Model Details
The Marketing Cloud Einstein Content Selection and Testing model optimizes customer engagement with email content using these
training algorithms, parameters, fairness constraints, and features.

Person or Organization
Salesforce Marketing Cloud Einstein

Model Date and Version

• August 2020

296
Marketing Cloud Einstein and Analytics Einstein Content Selection

• Minor changes can occur throughout the release

• Major changes can occur and are communicated via release notes

Model Type
Reinforcement learning, multi-armed bandit algorithms

General Information
The model measures engagement through the click-to-open rate (CTOR) in real time and selects image content when the email is
opened. As more opens occur, Einstein favors top-performing content, but the remaining content is still used at lower rates. In the
multi-armed bandit algorithm, the trade-off of optimizing for the highest-performing content versus continuing to experiment with
other content is referred to as “exploiting vs exploring.”
Data from each send or journey is a standalone experiment. Assets with the highest CTOR in one experiment are reevaluated in subsequent
experiments.
When using the model in a single batch send, stagger the send time to optimize the exploit phase. Einstein collects the most engagement
data before new open events. To stagger sends automatically, use Einstein Send Time Optimization.
If a large portion of your audience uses Apple Mail Privacy Protection, Einstein needs a larger amount of opens before providing the
audience engagement data, resulting in a longer exploration phase. The longer phase could negatively impact your engagement rate
compared to non-Einstein content sends. To counter this effect, stagger your sends.
To personalize content in the Einstein Content Selection catalog, use the profile sync, content metadata, and Must Match attribute rules.
These rules narrow which catalog content that an individual can be exposed to in the experiment. If the personalization rules remove
content from the experiment, the remaining content that has the highest CTOR is the content to exploit.

Licenses
Einstein Content Selection and Einstein Content Testing are available to Salesforce Marketing Cloud customers with these editions.
• Pro
• Corporate
• Enterprise
• Enterprise+

Questions or Comments
Send questions or comments about the model to mce-support@salesforce.com.

Intended Use
The Marketing Cloud Einstein Content Selection and Testing model is intended for these use cases.

Primary Intended Uses

• Improve email engagement by experimenting and optimizing for the highest performing content.
• Personalize and manage the selected content using the provided Einstein Content Selection business rules.
• Use a simplified approach for how tested content is selected using Einstein Content Testing. ECT uses the same Einstein algorithm
with traditional A/B/n testing, but simplified and without personalization or other business rules to manage how content is selected.

297
Marketing Cloud Einstein and Analytics Einstein Content Selection

Out-of-Scope Use Cases

• Don’t use Einstein Content Selection or Testing for text content in emails or subject line testing because Einstein content runs
open-time experiments.
• Don’t use Einstein Content Selection or Testing to test top-performing content across different sends or journeys.

Relevant Factors
These factors are associated with the Marketing Cloud Einstein Content Selection and Testing model.

Model Input
The Einstein model that powers Content Selection and Content Testing analyzes content performance for each send or journey.

Model Output
Content to display for a given email open event.

Groups
The model doesn’t include demographic data or other data purchased from third-party data providers.

Environment
The model is trained and deployed in the Salesforce Marketing Cloud environment.

Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance measures
are associated with the Marketing Cloud Einstein Content Selection and Testing model. Customers are responsible for monitoring the
accuracy of Einstein Content Selection.

Model Performance Measures

Model performance metrics include data such as click-to-open rate (CTOR) and click-through rate (CTR). All metrics are aggregated and
anonymized.

Training Data
You have a customized version of the model that’s trained on your data alone. Data from one Salesforce customer doesn’t affect the
behavior for another Salesforce customer. While model training happens for each customer on their data, the initial development of the
model is validated with a representative set of pilot customers’ data.

Ethical Considerations
Review the ethical factors associated with the Marketing Cloud Einstein Content Selection and Testing model. To avoid bias and other
ethical risks, the Einstein Content Selection and Testing model doesn’t include demographic data. Further bias is mitigated by training
the model with a robust content catalog.

298
Marketing Cloud Einstein and Analytics Einstein Content Testing

Einstein Content Testing

To optimize engagement, quickly test images in Einstein Content Testing. For more complex
EDITIONS
personalized targeting, use Einstein Content Selection, which includes fatigue rules and targeted
content based on user preferences. Available in: Professional,
Content Testing consumes Einstein Content Selection Impressions, which is a type of Super Message. Corporate, and Enterprise
Images are selected in real time, so Super Messages are consumed only when an email open event Editions
is received. For more information, see Multipliers for Marketing Cloud and Marketing Cloud Data
Usage Types.
With automated testing, Einstein runs a multi-armed bandit test that balances optimization of winning content with open-time
experimentation for the duration of the test. The winning content can be dynamic, and is defined as content with the highest click-to-open
rate at the time an open event is received. Winning content is selected more often than the remaining experimental content. This
experiment type is intended for continual self-regulation, although you can opt to select a winner so that all subsequent opens receive
the same content. The automated test is best for longer duration sends, such as a long-running journey or a send that’s managed by
Einstein Send Time Optimization, or when you don’t want to self-manage the experiment. See the model card for more details.
The manual approach equally distributes content until a winner is determined. You can either identify a winner manually after reviewing
the results or have the winner determined after a certain number of clicks is reached. If you want the winner to be determined, the
content with the highest click-to-open rate is selected when the click threshold is reached. Manual tests work well when you’re
experimenting with a test audience and the winner determines which content to include in subsequent large batch sends. Manual
testing is also useful when experimenting for a long running Journey and if you want more control around when a winner is determined.
25

Create a Content Test

Use Einstein Content Testing to compare up to 32 images to determine what works best. You can create automated tests or manual
A/B/n tests. You can also access previous tests on the Content Test page. Draft, completed, and archived tests aren’t available.
Delete a Content Test Draft
When a test draft is no longer needed, you can delete it.
Stop a Content Test
You can stop a manual or automated content test at any time. For example, you might want to stop a manual test after you’ve
received engagement data on a few thousand opens. Generally, you don’t need to stop an automated test unless you want to
override the continual testing portion and ensure that all images are optimized to a single asset.
Archive a Content Test
Clean up your list of content tests by archiving tests that are no longer relevant.
View Content Test Performance
To increase your subscriber interactions, use the performance results data to review the click rate and open rate and guide your
messaging.

Create a Content Test

Use Einstein Content Testing to compare up to 32 images to determine what works best. You can create automated tests or manual
A/B/n tests. You can also access previous tests on the Content Test page. Draft, completed, and archived tests aren’t available.
See Einstein Content Testing on page 299 for information about the difference between automated and manual testing. To personalize
contest testing, assign content to placements in your email template. You can also apply rules to your test (see Einstein Content Block).

25
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

299
Marketing Cloud Einstein and Analytics Einstein Content Testing

1. In Einstein Content Testing, click Content Test.

2. Click New Test.
3. Name and describe the test so that others can find it.

Tip: Use the description to record what you’re testing, give context to your test results, and let others know why the test was
created.

4. Click Next.
5. Add or select the files to test, and click Next.
6. Select a test mode.
• To send the content asset that is winning to more recipients, use the Automated Test distribution test mode on page 299.
• To send the same number of messages to recipients of each content asset that you’re testing, use the Manual Control distribution
test mode on page 299.
a. If you select the Manual Control distribution test mode, tell Einstein how to determine the winner.
b. Set the selection or click total to indicate the test’s duration.

7. Click Next.
8. Review your settings.
9. To start testing, publish the test and then create a Contest Testing Block in Content Builder.

SEE ALSO:
Use Einstein-Tested Content in Your Emails
Use Einstein-Tested Content in Your Emails

Delete a Content Test Draft

When a test draft is no longer needed, you can delete it.
You can only delete content test drafts. To remove a completed test from your list of active tests, archive it.
1. In Einstein Content Selection, click Content Test.
2.
Next to the test to delete, click .
3. Click Delete.

SEE ALSO:
Archive a Content Test
Archive a Content Test

Stop a Content Test

You can stop a manual or automated content test at any time. For example, you might want to stop a manual test after you’ve received
engagement data on a few thousand opens. Generally, you don’t need to stop an automated test unless you want to override the
continual testing portion and ensure that all images are optimized to a single asset.
1. On the Einstein Overview page, click the test that you want to stop.

300
Marketing Cloud Einstein and Analytics Einstein Content Tagging

2. Click Stop Test.

3. Choose the winning asset for subscribers to see in subsequent message opens.

Archive a Content Test

Clean up your list of content tests by archiving tests that are no longer relevant.
1. In Einstein Content Selection, click Content Test.
2.
Next to the test to archive, click .
3. Click Archive.

Access archived tests by clicking next to Active Tests.

View Content Test Performance

To increase your subscriber interactions, use the performance results data to review the click rate and open rate and guide your messaging.
1. On the Einstein Overview page, click the test that you want to review.
2. Scroll to the performance result details.

Einstein Content Tagging

Einstein Content Tagging automatically applies searchable tags to image files in your Marketing Cloud account. You can tell Einstein to
add up to 25 tags per image. Einstein tags existing JPG, JPEG, and PNG files that are 10 MB or less.
Before the February 2022 release, a configurable prefix is added to all Einstein tags to distinguish them from tags added by users. The
default prefix is MCECT. After the February 2022 release, you can optionally upgrade to a nested tagging structure and suffix. For more
information see Set Up Nested Einstein Content Tags.
Einstein analyzes and tags new images one time every 24 hours. New images are automatically tagged based on account limits.

Note: This feature uses Google Vision to analyze and process image files. To learn more, visit Google Vision.

Table 11: Annual New Image Limits

Account Level Maximum Number of New Images
Enterprise 4,000

Corporate 2,000

Professional 1,000

26

26
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

301
Marketing Cloud Einstein and Analytics Einstein Content Tagging

Einstein Content Tagging Confidence Level

With Einstein Content Tagging, you can select the confidence level between 0.5 (lowest) and 1.0 (highest) to use for automatic tags
in Marketing Cloud. Use a higher confidence level to improve the accuracy of the tags applied to your images. Use a lower confidence
level to broaden the scope of tags included.
Set Up Einstein Content Tagging
Configure Einstein Content Tagging (ECT) in the Marketing Cloud Setup app. Some settings can’t be modified after you configure
them, but you can update tagging language and tagging location at any time.
Modify the Tagging Language
Select from one of over 100 languages to use when automatically tagging images.
Disable, Delete, or Reset Einstein Content Tags
You can pause automatic tagging, remove existing automatically generated tags, or reset Einstein-generated tags within a single
business unit. Pause automatic tagging by disabling Einstein Content Tagging (ECT). Then you can resume tagging, delete tags, or
reset tags.
Gauge Content Performance Using Einstein Content Tags
See the content tags that Einstein generates in Einstein Content Selection Performance Analytics to understand which aspects of
your content are performing well.

Einstein Content Tagging Confidence Level

With Einstein Content Tagging, you can select the confidence level between 0.5 (lowest) and 1.0 (highest) to use for automatic tags in
Marketing Cloud. Use a higher confidence level to improve the accuracy of the tags applied to your images. Use a lower confidence level
to broaden the scope of tags included.
This feature is powered by Google Vision. Vision analyzes the pixels and patterns of your image and searches its extensive repository for
matching patterns in previously tagged images. Vision’s confidence level is determined by how often it has analyzed similar images and
the distinctiveness of the tags applied. To learn more, visit Google Vision.

Set Up Einstein Content Tagging

Configure Einstein Content Tagging (ECT) in the Marketing Cloud Setup app. Some settings can’t be modified after you configure them,
but you can update tagging language and tagging location at any time.
You can’t modify maximum tags per image, tagging prefix, or tagging confidence level when Einstein Content Tagging is active. To
modify these settings, turn off ECT and delete its tags.
1. In the Marketing Cloud Setup app, expand Einstein and click Einstein Content Tagging.
2. Click Settings.
3. Enter the maximum number of tags per image, up to 25.
4. Enter an alphanumeric prefix for the tag to help users distinguish between tags you add and tags added by Einstein Content Tagging.
5. Select the confidence level between 0.5 (lowest) and 1.0 (highest).

Tip: Start by setting the confidence level to 0.75, then adjust the confidence level based on tagging results.

6. Click Save.
7. Select the tagging location.
8. Select the language.
9. Turn on Einstein Content Tagging.

302
Marketing Cloud Einstein and Analytics Einstein Content Tagging

Modify the Tagging Language

Select from one of over 100 languages to use when automatically tagging images.
• Einstein Content Tagging defaults to tagging images in English.
• You can modify the tagging language at any time. But the newly chosen language is applied to automatically applied tags only.
Einstein doesn’t modify tags that you create.
• Tags are updated one time every 24 hours. Only newly uploaded or modified images are tagged.
1. In the Marketing Cloud Setup app, expand Einstein and click Einstein Content Tagging.
2. Select a Language in the Select Einstein Content Tagging Language section.
3. Click Update.
New and newly modified image tags are updated to appear in the new language within 24 hours.

Disable, Delete, or Reset Einstein Content Tags

You can pause automatic tagging, remove existing automatically generated tags, or reset Einstein-generated tags within a single business
unit. Pause automatic tagging by disabling Einstein Content Tagging (ECT). Then you can resume tagging, delete tags, or reset tags.
• To delete existing tags, turn off ECT first.
• To modify tagging settings, delete existing tags. But to modify tagging language or tagging location, it’s not necessary to delete
tags.
• Deleted tags can’t be restored.
• Wait 24 hours after deleting tags to re-enable ECT. If you delete tags before Einstein Content Tagging is re-enabled, all images are
retagged using the settings defined.
• If you don’t delete images before re-enabling ECT, ECT resumes tagging using the previous settings. Previous tags are updated only
if the image is modified.
1. In the Marketing Cloud Setup app, expand Einstein and click Einstein Content Tagging.
2. Turn off Einstein Content Tagging.

Tip: To temporarily pause automatic tagging, stop here. Turn ECT back on any time.

3. Click Delete.
4. Click Delete Tags.
5. Click Delete.

Note: Deleting tags for your business unit can take up to 24 hours.

6. If necessary, update the tagging settings, location, and language.

Tip: You can modify tagging settings after deleting existing tags.

7. Turn on Einstein Content Tagging.

Gauge Content Performance Using Einstein Content Tags

See the content tags that Einstein generates in Einstein Content Selection Performance Analytics to understand which aspects of your
content are performing well.

303
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Use Einstein Content Tagging with Einstein Content Selection to gain more insight into which types of content perform best for your
audience. Einstein uses AI to analyze and tag content selection assets according to what’s in the image. Correlating the tags with selections
and clicks can help show which aspects of your content are meaningful to your audience.
• Enable Einstein Content Tagging in Marketing Cloud Setup’s Einstein Content Selection settings.
• Find out the types of content tags that perform best and the total of each type with Einstein Content Selection Performance Analytics.

Einstein Email Recommendations

Use Einstein Email Recommendations to observe customer behavior, build preference profiles, and deliver the next-best content or
product. You can also refine recommendations to match your business rules. Recommendation content surfaces in placeholders for
recommendations on your website.
Email recommendations are delivered as a pre-built image and link pair and are activated when a user engages with the email. We refer
to email recommendations as engagement recommendations, meaning the logic and scenarios are processed immediately before they
see the recommendation.
The image in the recommendation is based on an HTML template that is used to style what one recommendation would look like. Each
product or content recommendation is generated ahead of time and stored to ensure that the image is instantly available. By pre-processing
displays and logic for each product or content recommendation, the most up-to-date recommendation is delivered without sacrificing
performance when a subscriber engages with the email.
Here’s the required HTML that that is included in an email template for a block with two recommendations.
<a href="https://MID.recs.igodigital.com/rr/v2/HASH/l/1/%%emailaddr%%">
<img src="https://MID.recs.igodigital.com/rr/v2/HASH/i/1/%%emailaddr%%">
</a>
<a href="https://MID.recs.igodigital.com/rr/v2/HASH/l/2/%%emailaddr%%">
<img src="https://MID.recs.igodigital.com/rr/v2/HASH/i/2/%%emailaddr%%">
</a>

Here’s the HTML to create the image used in this call.

<div style="font-size:12px;color:black;width:150px; text-align:center;">
<img style="max-width:150px;" src="%%ImageLink%%">
<p><b>%%ProductName%%</b></p>
%%[ if SalePrice &lt; RegularPrice then ]%%
<s>Regular Price: %%RegularPrice%%</s><br>
<span style="color:red;">Sale Price: %%SalePrice%%</span>
%%[ else ]%%
%%RegularPrice%%
%%[ endif ]%%
<p>%%Description%%</p>
</div>

Here’s an example of the image generated and called via the link in the email recommendations. The link redirects to the page on the
site while tracking the click:

304
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Each recommendation is an individual image, so if you needed four recommendations in a call, the HTML would include four image and
link pairs. The display of the recommendation is unified across the entire recommendation, so with engagement recommendations, all
four recommendations use the same HTML and AMPscript. Because email recommendations are displayed as an image, consider the
mobile responsiveness of the design.
For information about how recommendations are applied to messages, see Multipliers for Marketing Cloud.
27

Einstein Email Recommendations Dashboard

The email recommendations dashboard in Einstein Recommendations displays a list of available recommendations. From here, you
can create, edit, or delete a recommendation.
Create Einstein Email Recommendations
Follow these steps to create Einstein Email Recommendations.
Supported Fonts
Einstein Email Recommendations supports multiple fonts.
Einstein Recommendations
Einstein Recommendations deliver the next best product, content, or offer to every individual through product and content
recommendations for email and web. Every customer interaction is an insight. With every click, download, view, and purchase,
customers are giving data about their preferences. Einstein Recommendations combine user behavior with algorithms and your
unique business rules to build a user profile of affinities. Use that profile to determine the most relevant content and products for
each customer in real time.

Einstein Email Recommendations Dashboard

The email recommendations dashboard in Einstein Recommendations displays a list of available recommendations. From here, you can
create, edit, or delete a recommendation.
The dashboard appears when you open Einstein Web Recommendations. To return to the dashboard, click Overview.
The dashboard includes:
• the recommendation name
• the selected display

27
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

305
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

• the recommendation ID
• the gear icon

Tip: To delete or edit a recommendation or get the code, click the gear icon .
28

Create Einstein Email Recommendations

Follow these steps to create Einstein Email Recommendations.

Note: When a customer profile privacy is set to one the following, the system generates generic recommendations from the
scenarios you configured.
• Do Not Track
• Do Not Profile
• Do Not Process
For example, if you configure View as the top scenario, a visitor who views a product detail page sees recommendations for
products that other customers also viewed.
29

1. Create Einstein Email Recommendations Content

Determine what content to include in the recommendation.
2. Create Einstein Email Recommendations Logic
Use Einstein Email Recommendations in to create custom recommendations logic or choose from the list.
3. Configure the Einstein Email Recommendations Layout
Determine the layout for how recommendations appear.
4. Configure an Einstein Email Recommendations Scenario
Choose the recommendation scenarios to use in Einstein Email Recommendations.

28
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.
29
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

306
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

5. Insert Einstein Email Recommendations Code

Copy and insert Einstein Email Recommendations code into your email.

Create Einstein Email Recommendations Content

Determine what content to include in the recommendation.
1. To create a custom display, click Create New. To choose a standard display, hover over the image and click Select or Edit and go
to step 3.
2. For a custom display, enter a name and click Create.
3. Create.
4. Select an identifier to add to the display and click Add. To include more identifiers, repeat this step.
Code for your selections appears.
5. Click Preview.
A visual preview appears.
6. To save your display without publishing, select Stage Changes. Or click Save and Publish.

Note: Publish the content before using it in an email.

7. Click Exit.
30

Create Einstein Email Recommendations Logic

Use Einstein Email Recommendations in to create custom recommendations logic or choose from the list.
1. Navigate to Einstein and click Einstein Email Recommendations.
2. To use standard logic, click the name.
3. Or, click Create New Logic .
a. To create custom logic, enter a name.
b. Select a catalog.
c. Click Create.

The Display tab appears.

30
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

307
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Configure the Einstein Email Recommendations Layout

Determine the layout for how recommendations appear.
1. Click the Logic tab and click the Layout tab.
2. To select the number of columns and rows for the recommendations content, hover over the grid, and click the last cell to include.
For example, to render in the columns with two rows, click the cell labeled 3X2.

3. Click Preview.
4. Edit your selection, if necessary.
5. Click Save.
31

Configure an Einstein Email Recommendations Scenario

Choose the recommendation scenarios to use in Einstein Email Recommendations.
1. Click the Scenarios tab.
2. Select a scenario from the list and click Add.

Note: For details about what each scenario does, see Einstein Recommendation Scenarios.

The scenario appears on the canvas. It automatically applies to all recommendation areas.
3. Click all areas and select a recommendation area from the dropdown list.
4. To add more scenarios, repeat steps 2 and 3.

Tip: To remove a scenario from the canvas, click .

Tip: Einstein Recommendations returns predictions from the top ranked scenario.

5. To preview the recommendations, click Preview.

31
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

308
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

6. To reorder the priority of scenarios, drag them into the order from top to bottom on the canvas.
7. To use waterfall predictions, select Enable Waterfall Prediction.

Tip: Learn more about Waterfall Predictions.

8. To suppress system-generated scenarios, select Disable System Scenarios.

9. Click Save.

Note: To restore the default scenario configuration, click Restore to Default Best Practices and click Save.

10. Click Exit.

32

Insert Einstein Email Recommendations Code

Copy and insert Einstein Email Recommendations code into your email.

Tip: To customize how recommendations render in an email, use AMPscript.

1. Click the Logic tab and click the recommendation to use.

2. Click the Get Code tab.
3. Note: Einstein Contact Code generates content in a preview only after you select a subscriber.

To preview the recommendation, click Preview.

4. Copy the code.
5. Paste the code into the body of the email.
33

AMPscript Functions for Einstein Email Recommendations

View a list of commonly used AMPscript functions for Einstein Email Recommendations.

AMPscript Functions for Einstein Email Recommendations

View a list of commonly used AMPscript functions for Einstein Email Recommendations.
Use these functions to define email image templates, or for conditional formatting, data formatting, and sanitizing.

Product Attributes
Replace the attribute name with the attribute value of the item to recommend.

Example: %%AttributeName%%

Conditional Operators
Conditional statements allow conditional display and formatting, such as a strikethrough over the regular price when items are on sale.

32
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.
33
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

309
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Operators where A and B can be a:

• string
• float
• product attribute or exact name from your catalog, such as %%WidthInInches%%

A>B True when A is greater than B

A<B True when A is less than B

A >= B True when A is greater than or equal to B

A <= B True when A is less than or equal to B

A == B True when A equals B

A!= B True when A isn’t equal to B

Example:

%%[ if a > b then ]%%

print this if statement is true
%%[ else ]%%
optional line that will print if statement if false
%%[ endif ]%%

Logical Operators
Use logical operators to make compound conditions in if statements. Use only one logical operator in a condition.

&& Logical And - Executes when both conditions are true.

|| Logical Or - Executes when either condition is true.

Example: %%[ if a > b || b > c then ]%%

Print if at least one condition is true
%%[ endif ]%%
%%[ if a > b && b > c then ]%%
Print if both conditions are true
%%[ endif ]%%

Conversion Functions
ToFloat
Appending an item attribute key with ToFloat converts the value of a string field in your catalog to a floating-point number.

310
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Example: %%WidthInInches%% 12
%%WidthInInchesToFloat%% 12.0

LengthNum
Appending an item attribute key with LengthNum returns the length of the value in your catalog. Use LengthNum only within the
statement.

Example: %%[if DisplayRegularPriceLengthNum < 5 then ]%% %%ProductName%% %%[else]%%

%%DisplaySalePrice%% %%[ endif ]%%
LongestWordLength
Append LongestWordLength to an item attribute key to convert the value to a string. This function calculates the longest word then
returns a number for the length of that word.

Example: %%Description%%
I love Einstein Email Recommendations
%%DescriptionLongestWordLength%%
15

Display Functions
Rating Stars
Take the value stored in the Rating field and convert it to the number of stars where:
• maximum_value is the highest ranking
• color is the color of the stars
The rating comes from the product's Rating attribute.

Example: %%= RatingStars(maximum_value, color) =%%

RegularPriceMain or SalePriceMain
Outputs the integer part of the field mapped to RegularPrice or Price for streaming updates and SalePrice.

Example: %%RegularPriceMain%% 34
%%SalePriceMain%% 29

RegularPriceFractional or SalePriceFractional
Outputs the fractional part of the field mapped to RegularPrice or Price for using streaming updates and SalePrice.

Example: The following example assumes that the recommended item is regularly priced 34.50, but on sale for 29.99.
%%RegularPriceFractional%% 50
%%SalePriceFractional%% 99

ToUpcase
Outputs the value in the catalog in uppercase.

Example: %%AuthorToUpcase%% MARK TWAIN

FirstN

311
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Where N is a whole number, outputs first N characters of value.

Example: %%AuthorFirst6%% Mark T

Split
Usage: SplitDAtI
Where D is the delimiter and I is the index, splits the value returns the string at the given index. Delimiter can be longer than 1 character
and index can be negative.

Note: Currently the Split function can’t be used inside an IF condition.

Example: When the value for Colors is Red~Blue~Green: %%ColorsSplit~At1%% Blue

Replace
Usage: ReplaceAWithBEnd
Where A is the match substring and B is the replacement substring, replaces the matches globally and outputs the value.

Example: %%AuthorReplaceMarkWithSamuelEnd%% Samuel Twain

UpTo
Usage: UpToNByDWithOEnd
Where N is a whole number, D is the delimiter, and O is an optional overflow text, outputs the value up to the N index of D with O
appended when included. Values shorter than the limit return unaltered and values without a delimiter match within the limit returns
blank.

Example: If the value for LongTitle is “Long~Item~Title” %%LongTitleUpTo10By~With...End%%: Long~Item…

%%LongTitleUpTo9By~WithEnd%%: Long
%%LongTitleUpTo4By~WithEnd%%: blank
%%LongTitleUpTo9By~WithEnd%%: Long
%%LongTitleUpTo20By~WithEnd%%: Long~Item~Title

Chaining
You can chain multiple functions together.

Example: For example, if Author = Mark Twain %%Author%%: Mark Twain

%%AuthorReplaceMarkWithSamuelEndReplaceTwainWithClemensEndToUpCase%%: SAMUEL CLEMENS

Supported Fonts
Einstein Email Recommendations supports multiple fonts.

Font Style
Century Schoolbook L Bold

Century Schoolbook L Bold Italic

Century Schoolbook L Bold Italic

312
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Font Style
Century Schoolbook L Roman

DejaVu Sans Bold

DejaVu Sans Book

DejaVu Sans Mono Bold

DejaVu Sans Mono Book

DejaVu Serif Bold

DejaVu Serif Book

Dingbats Regular

Droid Sans Fallback Regular

Hind Vadodara Bold

Hind Vadodara Regular

Hind Vadodara Light Regular

Hind Vadodara Medium Regular

Hind Vadodara SemiBold Regular

IPAexGothic, IPAex Regular

IPAexGothic, IPAex Regular

IPAexMincho, IPAex Regular

IPAexMincho, IPAex Regular

Lato Bold

Lato Regular

Lato Black Regular

Lato Hairline Regular

Lato Light Regular

League Script Regular

Nimbus Mono L Bold

Nimbus Mono L Bold Oblique

Nimbus Mono L Regular

Nimbus Mono L Regular Oblique

Nimbus Roman No9 L Medium

Nimbus Roman No9 L Medium Italic

313
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Font Style
Nimbus Roman No9 L Regular

Nimbus Roman No9 L Regular Italic

Nimbus Sans L Bold

Nimbus Sans L Bold Condensed

Nimbus Sans L Bold Condensed Italic

Nimbus Sans L Bold Italic

Nimbus Sans L Regular

Nimbus Sans L Regular Condensed

Nimbus Sans L Regular Condensed Italic

Nimbus Sans L Regular Italic

Noto Mono Regular

Noto Sans Bold

Noto Sans Bold Italic

Noto Sans Italic

Noto Sans Regular

Noto Sans CJK JP,Noto Sans CJK JP Black Black, Regular

Noto Sans CJK JP,Noto Sans CJK JP Bold Bold, Regular

Noto Sans CJK JP,Noto Sans CJK JP DemiLight DemiLight, Regular

Noto Sans CJK JP,Noto Sans CJK JP Light Light, Regular

Noto Sans CJK JP,Noto Sans CJK JP Medium Medium, Regular

Noto Sans CJK JP,Noto Sans CJK JP Regular Regular

Noto Sans CJK JP,Noto Sans CJK JP Thin Thin, Regular

Noto Sans CJK KR,Noto Sans CJK KR Black Black, Regular

Noto Sans CJK KR,Noto Sans CJK KR Bold Bold, Regular

Noto Sans CJK KR,Noto Sans CJK KR DemiLight DemiLight, Regular

Noto Sans CJK KR,Noto Sans CJK KR Light Light, Regular

Noto Sans CJK KR,Noto Sans CJK KR Medium Medium, Regular

Noto Sans CJK KR,Noto Sans CJK KR Regular Regular

Noto Sans CJK KR,Noto Sans CJK KR Thin Thin, Regular

Noto Sans CJK SC,Noto Sans CJK SC Black Black, Regular

314
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Font Style
Noto Sans CJK SC,Noto Sans CJK SC Bold Bold, Regular

Noto Sans CJK SC,Noto Sans CJK SC DemiLight DemiLight, Regular

Noto Sans CJK SC,Noto Sans CJK SC Light Light, Regular

Noto Sans CJK SC,Noto Sans CJK SC Medium Medium, Regular

Noto Sans CJK SC,Noto Sans CJK SC Regular Regular

Noto Sans CJK SC,Noto Sans CJK SC Thin Thin, Regular

Noto Sans CJK TC,Noto Sans CJK TC Black Black, Regular

Noto Sans CJK TC,Noto Sans CJK TC Bold Bold, Regular

Noto Sans CJK TC,Noto Sans CJK TC DemiLight DemiLight, Regular

Noto Sans CJK TC,Noto Sans CJK TC Light Light, Regular

Noto Sans CJK TC,Noto Sans CJK TC Medium Medium, Regular

Noto Sans CJK TC,Noto Sans CJK TC Regular Regular

Noto Sans CJK TC,Noto Sans CJK TC Thin Thin, Regular

Noto Sans Mono CJK JP,Noto Sans Mono CJK JP Bold Bold, Regular

Noto Sans Mono CJK JP,Noto Sans Mono CJK JP Regular Regular

Noto Sans Mono CJK KR,Noto Sans Mono CJK KR Bold Bold, Regular

Noto Sans Mono CJK KR,Noto Sans Mono CJK KR Regular Regular

Noto Sans Mono CJK SC,Noto Sans Mono CJK SC Bold Bold, Regular

Noto Sans Mono CJK SC,Noto Sans Mono CJK SC Regular Regular

Noto Sans Mono CJK TC,Noto Sans Mono CJK TC Bold Bold, Regular

Noto Sans Mono CJK TC,Noto Sans Mono CJK TC Regular Regular

Oswald Bold

Oswald Light

Oswald Regular Regular

Standard Symbols L Regular

URW Bookman L Demi Bold

URW Bookman L Demi Bold Italic

URW Bookman L Light

URW Bookman L Light Italic

URW Chancery L Medium Italic

315
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Font Style
URW Gothic L Book

URW Gothic L Book Oblique

URW Gothic L Demi

URW Gothic L Demi Oblique

URW Palladio L Bold

URW Palladio L Bold Italic

URW Palladio L Italic

URW Palladio L Roman

Einstein Recommendations
Einstein Recommendations deliver the next best product, content, or offer to every individual through product and content
recommendations for email and web. Every customer interaction is an insight. With every click, download, view, and purchase, customers
are giving data about their preferences. Einstein Recommendations combine user behavior with algorithms and your unique business
rules to build a user profile of affinities. Use that profile to determine the most relevant content and products for each customer in real
time.

Tip: Your web administrator can help you to configure and install Collect Tracking Code and required data feeds.

Before you attempt to use Einstein Recommendations, the setup wizard walks you through the steps to import a catalog and configure
Collect Tracking Code.

Note: Best practice is to observe website behavior for at least 30 days before launching any predictive content logic. This 30-day
monitoring period allows the engine to dynamically build profiles and behavioral intent patterns of your user base.
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

Einstein Recommendations Prerequisites

Learn about the prerequisites for implementing Einstein Recommendations.
Catalog
A catalog includes all fields that contain attributes used to make Einstein Recommendations. Einstein Recommendations filters assets
based on these attributes. For instance, you can define assets in the recommendation pool based on a product’s color or size, or an
article’s author and subject matter.
Einstein Recommendations Customer Profile Dashboard
Review a customer profile from this Marketing Cloud dashboard. Expand the view for greater detail or make changes to the customer
privacy setting.
Einstein Recommendations Integrations
Integrate data gathered through Einstein Recommendations with Audience Builder and Contact Builder.
Einstein Recommendations Status Console
Marketing Cloud Einstein Recommendations Status Console monitors the Collect Tracking Code and catalog import for common
implementation errors. View where an error occurred and details to help resolve the issue.

316
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Fix an Implementation Error

Follow these steps to fix an implementation error from the Einstein Recommendations status console.
Einstein Recommendations Rule Manager
Use Rule Manager to refine Einstein Recommendations for email and web.
Einstein Recommendation Scenarios
These scenarios help you produce Einstein Recommendations for email or the web in Marketing Cloud.
Waterfall Predictions
When you enable waterfall predictions in Einstein Recommendations, the system begins with your top priority scenario and continues
down the list to your lowest priority scenario. At each step, it returns all available matching items until it reaches the total number
of recommendations you set.
Localized Recommendations
Configure Einstein Recommendations to deliver localized recommendations in multiple languages and currency values from a single
business unit.
Einstein Recommendations Reports
Learn about reports available in Einstein Recommendations.
Einstein Recommendations FAQs
Get the answers to frequently asked questions about Einstein Recommendations.

SEE ALSO:
Catalog
Fix an Implementation Error
Einstein Recommendation Scenarios
Einstein Email Recommendations
Einstein Web Recommendations

Einstein Recommendations Prerequisites

Learn about the prerequisites for implementing Einstein Recommendations.

Einstein Recommendations Requirements

• A catalog of assets used to sync with user behavioral data and determine which recommendations to show.
• Collect Tracking Code used to monitor key variables and events on your website at the user level.

Note: For more information, watch this video about setting up Einstein Recommendations.

You can import one file for each catalog type.

Tip: Your web administrator can help you to configure and install Collect Tracking Code and required data feeds.

Note: We recommend observing website behavior for at least 30 days before launching any predictive content logic. This 30-day
monitoring period allows the engine to dynamically build profiles and behavioral intent patterns of your user base.

317
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Catalog
A catalog includes all fields that contain attributes used to make Einstein Recommendations. Einstein Recommendations filters assets
based on these attributes. For instance, you can define assets in the recommendation pool based on a product’s color or size, or an
article’s author and subject matter.

Note: Einstein Recommendations requires a minimum number of attributes, which vary depending on the application or
specifications.
The catalog functionality is used for multiple purposes within Einstein Recommendations. Here are the major areas to consider when
consulting on what fields to add to a catalog:
• Support Collect: The catalog data passed via Collect ties to the catalog in the data via the Product Code (item) and SkuID (unique_id).
These fields must match the Collect data to ensure proper function.
• Build User Profiles: When collecting user-data, the catalog takes the view ID and uses the tagged fields to build the profile.
• Support Recommendation Generation: Any data from the catalog can be used to build the recommendation. The catalog is the only
access to the metadata used to produce recommendations.
• Locale and Language Support: If any attributes vary by a locale or language, add the field to the catalog.
• Support Attribute-Based Rules: Data that is in the catalog can support rule generation. For example, if you want only Men’s clothes
shown in a particular recommendation, a field like “gender” could support this rule. If a data type is not in the catalog, rules cannot
be generated for it.
Marketing Cloud accepts three types of catalogs:
• Product: Products available for purchase
• Content: Articles, blogs posts, videos, or other types of content available for view
• Banner: Image files such as hero graphics, calls to action, or offers
You can import one file for each catalog type.
34

Einstein Recommendations Catalog Field Definitions

Catalog fields store your catalog’s asset attributes for Marketing Cloud Einstein Recommendations. These attributes are both required
and recommended catalog fields. You can also add custom attributes. Catalog field values are limited to 1024 single-byte characters
or 512 double-byte characters.
Reserved Attributes
See a list of attributes that are reserved for specific use in Einstein Recommendations. You cannot use these attributes to store other
values.
Add Attributes
To add an attribute in Einstein Recommendations, create a field at the end of the default field list.
Configure Custom Attributes
Configure custom attributes to use for Einstein Recommendations.
Create a Catalog Field Mapping
Create a catalog field mapping in Einstein Recommendations to ensure that catalog heading names are mapped to the required
application field names.

34
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

318
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Import a Catalog
Import a catalog to use in Einstein Recommendations as a pipe-delimited value (PDV) flat-file format. The first row of data must be
the column headings and each line contains non-breaking spaces. The catalog import file contains at least two rows of catalog data
in addition to the headings. We recommend daily catalog updates to reflect the changes on the site by the next business morning.
You can arrange an alternative schedule. For improved reliability, image size is limited to 2 MB when using the CSV catalog import
option.
Catalog Summary
The Einstein Recommendations catalog summary includes the type of import used and the currently selected reminders interval.
The file history table in the Status Console includes the date, time, and status history of the catalog uploads.
Catalog FAQ
Get the answers to frequently asked questions about the Einstein Recommendations catalog feature.

Einstein Recommendations Catalog Field Definitions

Catalog fields store your catalog’s asset attributes for Marketing Cloud Einstein Recommendations. These attributes are both required
and recommended catalog fields. You can also add custom attributes. Catalog field values are limited to 1024 single-byte characters or
512 double-byte characters.

Catalog Requirements
• Leave the catalog field blank rather than populating it with a Null value.
• Text fields can’t include carriage returns, new lines, or HTML.
• All characters in the catalog must either be UTF-8 encoded or converted to valid HTML, except for the pipe and tilde reserved
characters.
• Items with a price of $0 are recommended and displayed with the price of $0.
• The final catalog file must be automated and uploaded daily with a unique static file name.

Product Catalog

Field Name Required Attribute Description

SkuID No Unique identifier for each product, specific
to the customer. This ID must match the
product SKU on the website and be passed
via Collect Tracking Code.

ProductCode Yes Used to identify a group of related products.

For example, a piece of apparel appears in
the catalog multiple times with a unique
SkuID for each size the product is available
in. All these size variations are sent with the
same ProductCode. The ProductCode value
cannot contain spaces or special characters.

ProductName Yes Used to identify a product in the title of

product detail pages.

319
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Field Name Required Attribute Description

ProductType Yes Product category is open to retailers. The
application maps your product types to our
internal catalog system.

ProductLink Yes URL to reach the product detail page.

ImageLink No URL to the product image displayed in the

recommendation.

RegularPrice No Regular price for the product. You can

display this value in strikethrough text for a
recommendation when a sale price is
available.

SalePrice No Sale price for the product. It displays if a

product is on sale.

OnlineAvailability Yes Indicates if a product is available for

recommendation. This field only accepts
two possible values, Y for available or N for
not available. If the field is not sent with the
feed, the default value is Y. If it is sent as N,
the product is not returned in
recommendations.

Content Catalog

Field Name Required Attribute Description

ContentID Yes Unique identifier for each piece of content,
specific to the customer. This ID matches
the content ID on the website and is passed
via Collect Tracking Code.

Title No Title of content included in

recommendations.

Link Yes URL to reach the content detail page.

ImageLink No URL of the image displayed in the

recommendation.

Author No Author of specific content used to influence

recommendations or to be displayed within
the recommendations.

Category No Content category or categories.

Availability Yes Indicates if content is available for

recommendation. This field only accepts
two possible values, Y for available or N for

320
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Field Name Required Attribute Description

not available. If the field is not sent with the
feed, the default value is Y. If it is sent as N,
the content is not returned in
recommendations.

Publication Date No Date of publication to the site. Use data

format of YYYY-MM-DD.

Keywords No Keywords that describe the content.

Banner Catalog

Field Name Required Attribute Description

BannerID Yes Unique identifier for each banner or offer,
specific to the customer. This ID matches
the banner ID on the website passed via
Collect code.

GroupID Yes Used to identify a group of related banners.

For example, the same banner could be
available in multiple sizes. Each size of the
banner must be sent with a separate
BannerID, and is linked together with a
matching GroupID.

Name No Used for easy identification and content

management.

Category No Offer category, aligned to the catalog values

sent for product and or content categories.

Link Yes URL to reach the banner or offer detail page.

ImageLink Yes URL to the banner image displayed in the

recommendation.

LocationSize Yes Size of the banner location. This value can

be a size value, such as 600x400, or a name
value, such as HeroHome.

PPC No Price Per Click used to calculate Key

Performance Indicators. Round to the
nearest 2 decimal places and send without
any currency symbols.

Availability Yes Indicates if the banner available for

recommendation. This field only accepts
two possible values, Y for available or N for
not available. If the field is not sent with the
feed, the default value is Y. If it is sent as N,

321
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Field Name Required Attribute Description

the banner is not returned in
recommendations.

StartDate No Banners are automatically excluded from

the recommendation pool before the start
date. Use a suggested date format of
YYYY-MM-DD.

EndDate No Banners are automatically excluded from

the recommendation pool on the end date.
Use a suggested date format of
YYYY-MM-DD.

Keywords No Used to describe the banner or offer.

Reserved Attributes
See a list of attributes that are reserved for specific use in Einstein Recommendations. You cannot use these attributes to store other
values.

Attribute Name Reserved Use

ReleaseDate The first date an item is available for recommendations. This field
is required for new arrivals recommendations. The recommended
format for this field is YYYY-MM-DD.

Rating The user rating displayed for an item. This field is used to create
ratings-based recommendations.

NumReviews The number of reviews an item received. This field is used to create
ratings-based recommendations based on items customers are
talking about.

Keywords Keywords are used to match attributes to the customer’s interests.

Description This field contains the full description of an item included in

recommendations. It must be plain text.

ProductFamily This field is used to group multiple ProductCodes; for example, the
ProductFamilyID can include 5 colors of a specific style of t-shirt.
These 5 colors are sent in the catalog as 5 unique ProductCodes,
with 6 SkuID's each.

Accessories A list of SKU IDs or ContentIDs defined by the manufacturer or

content team, used to create business rules. For example, these
products can be excluded from recommendations on the detail
pages if they are already being served to the user on this page. Use
a tilde (~) format for this list.

322
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Add Attributes
To add an attribute in Einstein Recommendations, create a field at the end of the default field list.
Attributes are data fields containing product or content characteristics such as color, dimension, brand name, subject, or author.
1. Enter the Attribute Name at the end of the column heading. Do not include spaces.
2. Specify the attribute value at the end of the attribute value list.
If an attribute has multiple values, separate them with a tilde (~). Values are limited to 1024 single-byte characters or 512 double
byte characters.

Product Record
Example: SkuID|ProductCode|ProductName|ProductType|ProductLink|ImageLink|RegularPrice|
SalePrice|OnlineAvailability|ProductCost|ProductFamilyID|ProductDescription|
BrandName|Manufacturer|Color|Material|Rating|NumReviews|ReleaseDate| Keywords
12345|XCode12345|Brand X Product Whiz 9000|Electronics|
http://www.companyx.com/product|http://www.companyx.com/product/image.jpg|
99.99||Y|59.99|YCode12345|An amazing product.|Brand X|Company X|Blue~Red|
Metal|4|25|2012-08-27|Technology~Music
The current way to delete a product is to change the product's Online Availability attribute within the Catalog prior to upload. In
the example above, change the Y in the field that preceeds 59.99 to N. After you upload the catalog file, the N value will prevent
the product from showing up in product recommendations.

Content Record
Example:
ContentID|Title|Link|ImageLink|Author|Category|PublicationDate|Keywords|Availability
12345|Crock Pot Lasagna Soup|http://www.companyx.com/lasagna_soup|
http://www.companyx.com/soup/image.jpg||Recipes|2014-01-01| Italian~Soup~Slow
Cooker|Y

Banner Record
Example: BannerID|GroupID|Name|BannerType|Link|ImageLink|LocationSize|Category|PPC|
StartDate|EndDate|Keywords|Availability 12345|GRPABC|Free Shipping on 3+
Cookbooks|Shipping|
http://www.companyx.com/offer|http://www.companyx.com/offer/image.jpg|600x400|
Cookbooks~Slow Cooker|0.0025|2014-01-01|2014-03-31||Y

Configure Custom Attributes

Configure custom attributes to use for Einstein Recommendations.
Unmapped fields are automatically used by the Marketing Cloud to make recommendations. For Streaming Updates, Custom Attributes
Configuration is available after Marketing Cloud starts receiving data from your site.
Consider using these types of fields tags:
• Categories and Sub-Categories - . Mens, Womens, Kids, Coats, Shoes
• Brands - . Nike, Adidas, Under Armour

323
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

• Seasons - . Fall, Spring

• Topics - . Politics, Sports, Lifestyle
• Interests - Hiking, Golf, Cosmetics
Avoid these tags:
• Binary Values - . Binary values, such as Men or Women, could be good tags. We recommend reserving this option for the most
impactful values.
• Sizes or Colors and Other SKU Level Attributes- The recommendation engine aggregates behavior at the Product Code level. These
attributes on the SKU level could slant the results.
1. In Einstein Recommendations, hover over Admin and select Implementation.
2. Scroll to Custom Attributes.
3. Click Custom Attribute Configuration.
4. Select all fields included in the catalog.
5. Save.

Note: You receive an email when this configuration is enabled.

35

Create a Catalog Field Mapping

Create a catalog field mapping in Einstein Recommendations to ensure that catalog heading names are mapped to the required
application field names.
1. Click Field Mapping or click the gear icon and select Mapping.
2. Review the fields for mapping accuracy.
3. To change, expand the selection box under Your Headings and change the selections listed in the catalog heading names.
Unique catalog headings are required for each field. Duplication of a heading automatically deletes the heading from the previously
mapped field.

4. For Additional Fields, indicate if multiple values are accepted.

5. Select the tagged fields.
6. Select fields to be used for personalization.
7. Select a data format that matches the date field in your catalog.
8. Click Save.

35
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

324
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Example:

Import a Catalog
Import a catalog to use in Einstein Recommendations as a pipe-delimited value (PDV) flat-file format. The first row of data must be the
column headings and each line contains non-breaking spaces. The catalog import file contains at least two rows of catalog data in
addition to the headings. We recommend daily catalog updates to reflect the changes on the site by the next business morning. You
can arrange an alternative schedule. For improved reliability, image size is limited to 2 MB when using the CSV catalog import option.

Note: Merge data from disparate sources before importing into Marketing Cloud. The Marketing Cloud data services team can
help with data preparation. Contact your account representative for details.
The two catalog import options are:
• Daily Flat-File Upload. The daily flat file upload is added to an FTP account or publicly accessible web URL and imported into Einstein
Recommendations at the same time daily. A full upload of all products and a daily delta file is supported.
• Streaming Updates. The Streaming Update option adds and updates products and content through another snippet of Server-Side
JavaScript. All data must be available in the web layer sent in each call.
The data that is passed is the same no matter which method is chosen.

Tip: If you opt to use streaming updates and batch upload concurrently, both sources must contain the same data to avoid one
overwriting the other.
Visit Personalization Builder Catalog Field Definitions on page 319 for a list of required catalog fields.
Product Recommendation customers often have a product catalog already generated and decide to reuse or fashion the daily import
on something existing. Since the catalog data includes products, attributes, rules, and multiple languages the flat file catalog is often
the more appropriate choice. If a specific Product Code has numerous SkuID, the streaming update call includes data for each variation,
which can be a rather large payload. You can use Streaming Updates with Product Recommendations when all the data is available.
Content Recommendation clients are less likely to have a pre-created content catalog and often choose Streaming Updates. The data
layer of the website or CMS contains the content to add to the catalog and is easily added via JavaScript.
There’s no direct functionality to delete a product recommendation. The current way to delete a product is to change the product's
Online Availability via Attributes within the Catalog before upload. Set Online Availability for the product to N within the Catalog. This
action prevents the product from showing up in recommendations.
There are two ways to name the file to be uploaded daily. A static filename or a wildcard.
• Static Filename: The static filename is uploaded daily. We recommend that you replace it on the FTP before the upload kicks off. If
there are no changes in the file or a new one isn’t uploaded, the catalog import is skipped. An example of static filename would be
product_catalog.csv.

325
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

• Wildcards in Filename: You can add a wildcard (*) at the end of the filename that allows a new file name to be updated daily. Add
the date for the file at the end of the file and replace it with an asterisk (*) when adding to the upload UI.

Tip: We recommend that you use the naming format static_filename_YYYY_MM_DD.xxx. For example,
product_catalog_2018_01_01.csv. The filename is added to the upload as product_catalog_*. The filename
is sorted in descending order, so we recommend adding the year first to ensure that it sorts correctly.
1. In Email Recommendations or Web Recommendations, hover over Admin and select Implementation.
2. Select your catalog sync method.
3. To use streaming updates, enter your website domain name and click Register. If you don’t want to use streaming updates, you
can skip this step.
4. Choose a catalog type.
5. Select the format of your catalog.
6. Name your catalog.
7. Indicate if it’s a partial catalog.

Tip: To upload multiple files, use an asterisk in place of part of a file name as a wildcard. For example, to import
catalog_file_20130101.csv, catalog_file_20130102.csv, and catalog_file_20130103.csv, you can enter catalog_file_*.csv. The
system sorts the files in descending order and imports the top result. Use the YYYY_MM_DD date format when using dates
in wildcards to ensure that imports include the latest file.

8. To receive import status notifications and indicate the frequency of automatic notifications, enter an email address.
9. Click Upload New File.
10. To import more catalogs, repeat these steps.

Tip: You can cancel a catalog import before completion.

Note: You can only import one product, content, and banner catalog. When you do, previously imported catalogs of the
same type are overwritten.

Catalog Import Status

Learn about import statuses for a catalog import into Einstein Recommendations.

Catalog Import Status

Learn about import statuses for a catalog import into Einstein Recommendations.

Status Definition

Checking for an Available Product The system is confirming the availability of items in your catalog.

Duplicates Found for SKUID: [number] Catalog import completed successfully but found duplicate SKUIDs.

Error Uploading File A system error prevented initial file upload.

Field Mapping Required Your catalog’s field mapping is incomplete.

Import Queued No errors were found and the import begins.

326
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Problems: FTP Could not get the file. Often an issue where an FTP password or
username has changed

Problems: Parsing Illegal quoting. Double quotes are not encoded. Use \x22 as the
Unicode escape sequence for double quotation marks.

Successfully processed [number] items Your catalog imported successfully with a total of [number] items.

Problems: Unavailable Product The system found items listed as unavailable.

Processing Catalog Catalog import is in progress.

Processing errored before completion. OR Processing errored before An error occurred that stopped the import.
completion on SKUID: [number]

Requires Primary Key Mapping Select a Primary Key in field mapping.

Successful Imported without error.

System Error There was a failure in the process of receiving queue or status
messages.

Valid Imported with an error (such as a duplicate SKUID).

Validation Queued OR Validating The system is checking your catalog for errors.

Catalog Summary
The Einstein Recommendations catalog summary includes the type of import used and the currently selected reminders interval. The
file history table in the Status Console includes the date, time, and status history of the catalog uploads.
To view the summary, click the gear icon and select Summary or the catalog link in the catalog type column to view the catalog summary.

Note: Incomplete manual imports are excluded from the file history table.

You can view and change catalog settings and notifications under Settings.
• To change the catalog import or file type, select the dropdown menus for those fields. When prompted, complete the additional
required fields.
• To upload a new catalog file, select Upload New File. You advance to the catalog import page.
• To change the email notification address, enter a new address in the Email Notification field.
• You can also change the notification start date, frequency, and whether to receive notifications for failed catalog updates.
• If you select Refresh Current File and use an FTP or a URL file, the system immediately queues the file for import.

Note: Do not use this selection with Manual import type.

Catalog FAQ
Get the answers to frequently asked questions about the Einstein Recommendations catalog feature.

What Methods Are Available to Import a Catalog?

Your options are FTP, public URL for streaming, or manual upload.

327
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

What File Formats Are Supported for Catalogs?

It must be in UTF-8 format.
Can I Send Multiple Values in a Single Field?
Yes, as long as they are tilde-delimited (~). Standard fields do not support multiple values.
Can I Use My Current Marketing Cloud Catalog in Einstein Recommendations?
Yes, as long as it includes all required fields. Export it to your FTP account in UTF-8 format and then import it into Einstein
Recommendations.
Can I Use a URL as My ContentID?
It is not a best practice to use a URL as the ContentID. However, you can use a URL as your ContentID as long as that URL is fewer
than 256 characters.
Can Einstein Recommendations Import Offline Data Feeds?
Yes. A one-time historical data feed of online or offline purchases can be imported, in catalog format, as a part standard implementation.
This option is great for building “people who bought….also bought” lists, one of our highest revenue generating algorithms.
Can I Display Currency Denominations Other Than US Dollars?
Yes. Include the currency symbol in the Einstein Recommendations catalog and make it a text field outside of your standard pricing
fields.
How Many Decimal Places Must Pricing Fields Include?
We recommend including 2 decimal places.
Where Is Catalog Data Stored?
Catalog data is stored in Einstein Recommendations and exposed in Marketing Cloud through standard data extensions. To view
standard data extensions in your account, navigate to Data Extensions in Contact Builder.
Does Einstein Recommendations Integrate with Tag Management Vendors?
Yes, Einstein Recommendations integrates with tag management solutions. Many vendor partners created a template or other
customized method to add Collect Tracking Code to your content. Tag management can reduce page load time. It can reduce
implementation and maintenance time and effort.
Which Web Content Management Systems Integrate with Einstein Recommendations?
Einstein Recommendations is platform agnostic and can be implemented across any CMS.
When Do Recommendation Images Refresh?
Images refresh when a new display is published or manually refreshed. The images also refresh after one of these fields change via
a catalog file import or streaming update API call.
Can I Change an Item’s Product Code After the Initial Import?
No, don’t change the product code for a SKU ID after the initial import. Changing the product code creates a mismatch between
the Product Code and the UUID.

What Methods Are Available to Import a Catalog?

Your options are FTP, public URL for streaming, or manual upload.

What File Formats Are Supported for Catalogs?

It must be in UTF-8 format.

Can I Send Multiple Values in a Single Field?

Yes, as long as they are tilde-delimited (~). Standard fields do not support multiple values.

328
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Can I Use My Current Marketing Cloud Catalog in Einstein Recommendations?

Yes, as long as it includes all required fields. Export it to your FTP account in UTF-8 format and then import it into Einstein Recommendations.

Can I Use a URL as My ContentID?

It is not a best practice to use a URL as the ContentID. However, you can use a URL as your ContentID as long as that URL is fewer than
256 characters.

Can Einstein Recommendations Import Offline Data Feeds?

Yes. A one-time historical data feed of online or offline purchases can be imported, in catalog format, as a part standard implementation.
This option is great for building “people who bought….also bought” lists, one of our highest revenue generating algorithms.

Can I Display Currency Denominations Other Than US Dollars?

Yes. Include the currency symbol in the Einstein Recommendations catalog and make it a text field outside of your standard pricing
fields.

How Many Decimal Places Must Pricing Fields Include?

We recommend including 2 decimal places.

Where Is Catalog Data Stored?

Catalog data is stored in Einstein Recommendations and exposed in Marketing Cloud through standard data extensions. To view standard
data extensions in your account, navigate to Data Extensions in Contact Builder.

Does Einstein Recommendations Integrate with Tag Management Vendors?

Yes, Einstein Recommendations integrates with tag management solutions. Many vendor partners created a template or other customized
method to add Collect Tracking Code to your content. Tag management can reduce page load time. It can reduce implementation and
maintenance time and effort.

Which Web Content Management Systems Integrate with Einstein Recommendations?

Einstein Recommendations is platform agnostic and can be implemented across any CMS.

When Do Recommendation Images Refresh?

Images refresh when a new display is published or manually refreshed. The images also refresh after one of these fields change via a
catalog file import or streaming update API call.
These fields include:
• ProductName
• ImageLink
• OnlineAvailability
• RegularPrice
• SalePrice
• Any other field used in an image template when the change is triggered by a streaming update

329
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Can I Change an Item’s Product Code After the Initial Import?

No, don’t change the product code for a SKU ID after the initial import. Changing the product code creates a mismatch between the
Product Code and the UUID.
If the product code is updated and you notice a mismatch between the Product Code and UUID inside your catalog, follow the instructions
in the Marketing Cloud Einstein Recommendations - Remove Current Catalog article.

Einstein Recommendations Customer Profile Dashboard

Review a customer profile from this Marketing Cloud dashboard. Expand the view for greater detail or make changes to the customer
privacy setting.
The top section of the dashboard shows recent items purchased, viewed, and added to a cart by the customer. This section includes a
picture and name of the item and its SKU.

The next section shows the top attributes of products the customer purchased, viewed, or added to a cart. This section includes a graphic
representation of the top customer affinities. Larger rectangles indicate a stronger affinity.

330
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

The next section shows a picture and the name of each product recommended to the customer according to the rules you configured.

331
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Use the buttons to expand the profile to view the code version of information in the dashboard or to manage privacy settings. See
Manage Einstein Recommendations Customer Profile Data Privacy on page 336 for more details about privacy settings for Einstein
Recommendations.

The expanded view displays the code version of the customer profile. If a privacy setting is enabled for the customer profile, a number
code appears on the last line of the code.

332
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

• 1 - Do Not Track
• 2 - Do Not Profile
• 3 - Do Not Track and Do Not Profile
• 4 - Do Not Process
• 5 - Do Not Track and Do Not Process
• 6 - Do Not Profile and Do Not Process
• 7 - Do Not Track, Do Not Profile, and Do Not Process

Einstein Recommendations Privacy Status Dashboard

View the Personalization Builder privacy status dashboard to track processing of customer privacy option requests.

333
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

View an Einstein Recommendations Customer Profile

View a customer profile in Einstein Recommendations.
Configure Suppression for Einstein Recommendations
For Einstein Recommendations, the default suppression period for customer profile deletion is 14 days. During the suppression
period, the system holds existing data but does not collect more. The system deletes all profile data at the end of the suppression
period. Follow these steps to change the default setting.
Manage Einstein Recommendations Customer Profile Data Privacy
To honor subscriber privacy and data protection preferences, manage consent, data deletion, and restriction of processing for a
customer profile in Einstein Recommendations. To export Einstein Recommendations data, contact your account executive for
assistance.

Einstein Recommendations Privacy Status Dashboard

View the Personalization Builder privacy status dashboard to track processing of customer privacy option requests.
The dashboard display includes:
• The customer’s emails address
• Requested privacy option
• Status for processing the request
• Where the option is applied
• Date the request was initiated
• Date the request was completed
Follow these steps to view the Einstein Recommendations privacy status dashboard.
1. Select either Email Recommendations or Web Recommendations under Einstein.
2. Click the Reporting tab.
3. Click Admin Tools.
4. Click Privacy Status.
5. Enter a profile ID or date range.
6. Click Apply.

Tip: You can view a maximum of 100 instances in the dashboard. For longer lists, export to a CSV file.

334
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

View an Einstein Recommendations Customer Profile

View a customer profile in Einstein Recommendations.
1. Click the Reports tab within Einstein Recommendations.
2. Click Contacts.
3. Enter the customer’s email address.
4. Click Go.

Tip: To view a random customer profile, click Load Random Profile.

Configure Suppression for Einstein Recommendations

For Einstein Recommendations, the default suppression period for customer profile deletion is 14 days. During the suppression period,
the system holds existing data but does not collect more. The system deletes all profile data at the end of the suppression period. Follow
these steps to change the default setting.
1. Select either Email Recommendations or Web Recommendations under Einstein.
2. Click the Reporting tab.
3. Click Admin Tools.
4. Click Privacy Settings.
5. Enter the number of days.

Note: The suppression range is 0–30 days.

6. Click Save.

335
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Manage Einstein Recommendations Customer Profile Data Privacy

To honor subscriber privacy and data protection preferences, manage consent, data deletion, and restriction of processing for a customer
profile in Einstein Recommendations. To export Einstein Recommendations data, contact your account executive for assistance.

Tip: For details about contact information stored in Einstein Recommendations, visit Customer Profiles on page 330.

Follow these steps to manage the privacy settings for a customer profile in Einstein Recommendations.
1. Select either Email Recommendations or Web Recommendations under Einstein Recommendations.
2. Click the Reporting tab within Einstein Recommendations.
3. Click Contacts.
4. Enter the customer’s email address.
5. Click Go.
6. Scroll to the bottom of the customer profile and click the button that corresponds with the requested privacy setting.
• Delete Profile: Permanently delete the customer profile including all past behavioral data.
• Delete Suppression: Set a suppression period to delay data deletion for up to 30 days of the request.
• Do Not Track: Past behavioral data is retained but future interactions are ignored.
• Do Not Profile: Behavioral data is collected but not used for recommendations.
• Do Not Process: Past behavioral data is retained and future interactions are collected but ignored.
A confirmation popup appears with request process details
7. Click OK.

Note: To remove Do Not Track, Do Not Profile, or Do Not Process restrictions click the corresponding button again. To remove or
change a suppression period, follow the steps to Configure Suppression for Personalization Builder on page 335.

336
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Note: Privacy settings configured in Einstein Recommendations are also applied to Web & Mobile Analytics but not Contact
Builder. To view the status of the request, view the Personalization Builder Privacy Status Dashboard on page 334.

Einstein Recommendations Integrations

Integrate data gathered through Einstein Recommendations with Audience Builder and Contact Builder.
• Audience Builder: Create customer segments using complex data dimensions.
• Contact Builder: Provide a single view of the customer across all channels.
Review these prerequisites to integrate Einstein Recommendations.
• Configure at least one catalog and Collect Tracking Code.
• Enable Einstein Recommendations data extensions.
• To run the scripts that begin building dimensions, contact your Marketing Cloud account representative with at least four days of
advance notice.

Integration with Audience Builder

Learn how the data from Einstein Recommendations integrates with Audience Builder. You can use this data to filter and segment
subscribers.
Einstein Recommendations Integration with Contact Builder
Einstein Recommendations passes raw data gathered via Collect Tracking Code into Contact Builder. The data is organized in up to
eight data extensions that enable you to search and filter information. Data is available to all tools that integrate with Contact Builder.

Integration with Audience Builder

Learn how the data from Einstein Recommendations integrates with Audience Builder. You can use this data to filter and segment
subscribers.
Einstein Recommendations's integration with Audience Builder provides a set of standard ecommerce dimensions based on these data
points:
• Products Purchased
• Products Browsed
• Search Term
• Visits and User Affinity
Each dimension provides filter categories used to segment audience you can export into Email Studio for targeted campaigns. Filter
categories include:

337
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Products Purchased Products Browsed Search Term Visits and User Affinity
Product Name (LTD) Browse Event Count (LTD) Search Browse Event Count Days Since Last Visit

Product Name (30, 60, 90 days) Name Term Average Days between Visits

Purchased Date SKU Date Average Time on Site

Purchased Days (date range) Date Days Behavioral User Affinity

Product SKU Days

Product SKU (30, 60, 90 days) Attribute

Attribute

Days Since Last Purchase

Average Order Value

Average Days Between

Purchases

Einstein Recommendations Integration with Contact Builder

Einstein Recommendations passes raw data gathered via Collect Tracking Code into Contact Builder. The data is organized in up to eight
data extensions that enable you to search and filter information. Data is available to all tools that integrate with Contact Builder.
Here are the possible data extensions.

Data Extension Name Description

Products IGO_PRODUCTS Standard product data imported via the
product catalog.

Product Attributes IGO_PRODUCTATTRIBS Extra product metadata imported via the

product catalog.

Customer Profiles IGO_PROFILES Top five attribute preferences for a

subscriber based on items viewed, placed
in cart, or purchased.

Purchases IGO_PURCHASES User-specific product purchase data.

Views IGO_VIEWS User-specific product view data.

Abandoned Cart PI_ABANDONED_CART_EVENT Not in use.

Abandoned Items PI_ABANDONED_CART_ITEMS Not in use.

Content PI_CONTENT Standard content data provided via the

content catalog.

Content Attributes PI_CONTENTATTRIBS Extra content metadata imported via the

content catalog.

Content Views PI_CONTENTVIEWS User-specific content view data.

338
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Data Extension Name Description

User Sessions PI_SESSIONS Not in use.

Session End PI_SESSION_ENDS Event that is triggered when a user closes a

browser session.

Predictive Scores PREDICTIVE_SCORES Scores bases on analysis of previous data

and events.

Find these data extensions in the SFMC Default DE's folder. You can move these data extensions to a subfolder within the same MID as
necessary. After enablement, these data extensions hold data about catalog items uploaded or streamed from Collect Tracking Code
installed on a website. This information includes recorded user interactions.

Warning: Do not delete these data extensions.

Note: You can’t alter or delete the Session Ends, Abandoned Cart Items, and Abandoned Cart Events data extensions.

Tip: To manage privacy settings via API, review Personalization Builder API developer documentation.

Turn On Einstein Recommendations Data Extensions

Enable Einstein Recommendations to populate data extensions in Contact Builder.
Customer Profile Data Extension in Einstein Recommendations
Marketing Cloud Einstein Recommendations customer profile data extensions store the top five attributes for customer affinity based
on behavioral data. The profile updates at the end of every customer session. You can delete a customer profile at any time.
Content
Learn how Einstein Recommendations store data in the content data extension.
Content Attributes
Learn how Einstein Recommendations stores information in the content attributes data extension.
Content Views
Learn how Einstein Recommendations stores information in the content views data extension.
Product Attributes
Learn how Einstein Recommendations data is stored in the product attributes data extension.

339
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Products
Learn how data gathered in Einstein Recommendations is stored in the products data extension.
Purchases
Data from purchases tracked in Einstein Recommendations is stored in the Purchases data extension.
Views
Learn how Einstein Recommendations stores data in the Views data extension.

Turn On Einstein Recommendations Data Extensions

Enable Einstein Recommendations to populate data extensions in Contact Builder.
1. Navigate to the Status tab in Einstein Recommendations.
2.

Click .
3. Click Data Extension Settings.
4. Toggle on Enable Einstein Data Extensions.
5. Click Save.

Customer Profile Data Extension in Einstein Recommendations

Marketing Cloud Einstein Recommendations customer profile data extensions store the top five attributes for customer affinity based
on behavioral data. The profile updates at the end of every customer session. You can delete a customer profile at any time.

Note: Einstein Recommendations is also known as Predictive Intelligence.

Field Attribute Definition

user_id System-assigned ID for a user

email User email address; to apply the Personalization Builder Integrations

on page 338, you must use the user's email address. For privacy
reasons, we recommend using a non-PII identifier or hashing the
email.

city Customer's city based on IP address

region Customer's region, province, or state based on IP address

country Customer's country based on IP address

attribute1:attribute5 Include the attribute type that the affinity is categorized under, as
defined in the catalog such as category, color, or size. These
attributes are ordered according to the relative affinity weight of
each attribute within a customer’s profile.

value1:value5 Include a specific instance of the attribute type ordered from

highest to lowest according to the relative affinity weight in a
subscriber’s profile.

340
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Note: Field attributes in this extension vary according to requirements specific to your catalog and algorithms applied.

Content
Learn how Einstein Recommendations store data in the content data extension.

Field Attribute Definition

content_id System-assigned ID for a content item

availability Indicates if a piece of content is live on the website.

title Title of a piece of content

UUID System-assigned ID for the product

Content Attributes
Learn how Einstein Recommendations stores information in the content attributes data extension.

Field Attribute Definition

content_id Required: Assigned ID for a content item

updated_at Required: Exact date and time a piece of content was last updated

attribname Optional: Category, type, genre, and so on, for a piece of content

attribvalue Optional: Unique instance of the attribute type that is associated

with the content

Note: Field attributes in this data extension vary according to your catalog’s specific requirements.

Content Views
Learn how Einstein Recommendations stores information in the content views data extension.

Field Attribute Definition

content_id System-assigned ID for a content item

user_id System-assigned ID for a specific user

session_id System assigned unique ID for a specific user session

search Search terms entered into your website by customers, or category

associated with the search term

timestamp Exact date and time of the recorded view

341
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Product Attributes
Learn how Einstein Recommendations data is stored in the product attributes data extension.

Field Attribute Definition

sku Required: SKU number of the product

attribname Optional: Category, type, class, and so on, of a product

attribvalue Optional: Unique instance of the attribute type that is associated

with the product

updated_at Optional: Timestamp of the most recent catalog update

Note: Field attributes in this extension vary according to requirements specific to your catalog and are not limited to the optional
fields listed here.

Products
Learn how data gathered in Einstein Recommendations is stored in the products data extension.

Field Attribute Definition

name Name of the product

regPrice Regular price of the product

salePrice Sale price of the product

UUID System-assigned ID for the product

sku SKU number

Purchases
Data from purchases tracked in Einstein Recommendations is stored in the Purchases data extension.

Field Attribute Definition

sku SKU number for the product purchased

price Price of the product purchased

quantity Quantity of specific product purchased

order_summary Number associated with this purchase

user_id System-assigned ID for a specific user

timestamp Exact date and time of the purchase

342
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Views
Learn how Einstein Recommendations stores data in the Views data extension.

Field Attribute Definition

sku SKU number for the product viewed by the customer.

user_id System-assigned ID for a specific user.

session_id System assigned unique ID for a specific user session.

search Search terms entered into your website by customers.

timestamp Exact date and time of the recorded view.

Einstein Recommendations Status Console

Marketing Cloud Einstein Recommendations Status Console monitors the Collect Tracking Code and catalog import for common
implementation errors. View where an error occurred and details to help resolve the issue.
This feature helps ensure that the Einstein Recommendations engine receives the data necessary to power optimal Einstein
Recommendations and behavioral triggers for campaigns and journeys.
Many errors or a spike in errors indicates that something changed. For example, a catalog import failed to import with new products.
These changes generate errors in views, carts, and conversions because they don’t match. If there is an issue to resolve, an alert appears
in the status column. Click the link in the description column to view the error and take steps to fix the issue.
The Status Console shows incoming Collect Tracking Code data by call type. For more details about Collect Tracking Code types, review
Collect Tracking Code on page 50.
Currently, the number of products with errors is limited to 100 SKUs. If there is a major problem with hundreds of errors, we recommend
that you check multiple times for new errors. There is no notification when there’s an increase in errors or decrease in traffic.

Tip: We recommend that you review error rates on a weekly or monthly basis.

Configure Einstein Recommendations Error Email Notification

Set up and enable email notifications in case Collect Tracking Code stops working within your Marketing Cloud Einstein
Recommendations implementation.

Configure Einstein Recommendations Error Email Notification

Set up and enable email notifications in case Collect Tracking Code stops working within your Marketing Cloud Einstein Recommendations
implementation.
1. Navigate to the Status tab in Einstein Recommendations.
2.

Click .
3. Click Notification Settings.
4. Enter at least one email address.
5. Select the number of hours to wait before alerting that data collection has stalled.
6. Enter the Collect Tracking Codes to monitor.

343
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

7. Click Save.

Fix an Implementation Error

Follow these steps to fix an implementation error from the Einstein Recommendations status console.
Complete these steps for each alert.

Note: If you only click Mark as Resolved, the error is not fixed. Follow the instructions in the window that opens from the error
link. If the error reoccurs, the alert reappears in the status console.
1. Click the error link in the Details column.
2. Click Take these steps to troubleshoot error.
3. Complete the steps in the pop-up window.
4. Click Mark as Resolved.
The alert in the status console changes to OK.

Einstein Recommendations Rule Manager

Use Rule Manager to refine Einstein Recommendations for email and web.
You can create rules for these things:
• All web and email recommendations.
• Specific SKUs with the ability to search the attribute field within the catalog.
• Product or content release date using the release date field in the catalog.
• Greater-than or less-than rules for dates and numbers (specifically prices) and ratings.
Contact Events are conditional statements to fulfill actions in rules only when the user meets specified criteria: Past purchase includes
a chosen attribute value. Past view includes a chosen attribute value. Last visit was greater than or less than X days ago.
Content Attributes are conditional statements to fulfill actions in rules only when the content being viewed meets specified criteria: All
catalog attributes available. Must reference item SKU ID in recommendation call to work properly. Attributes are case-sensitive.

Note: If you use a SKU ID that isn’t a master product in your catalog, the images don't generate correctly. Image generation is
applied only for master products.
The Actions section is the heart of the Rule Manager and lets you add business logic to the recommendation engine. The Rule Manager
limits or filters out recommendations based on a condition or makes certain characteristics more or less likely to be recommended within
a call.
36

Rule Manager Dashboard

Review the fields available in the Rule Manager dashboard in Einstein Recommendations.
Common Rule Types
To create your own algorithms, use rules in the Einstein Recommendations Rule Manager tool.
Configure a Rule
Configure a rule to refine Einstein Recommendations.

36
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

344
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Rule Manager Dashboard

Review the fields available in the Rule Manager dashboard in Einstein Recommendations.

Rule Name Description

Search Displays all rules containing the search term.

Configure New Rule Creates a rule.

Name Unique name for the rule.

Context Where you can apply the rule.

Status Indicates whether the rule is active or inactive.

Gears: Configure Edits the rule.

Gears: Settings Configures advanced rule settings.

Gears: Duplicate Duplicates the rule.

Gears: Delete Permanently removes the rule.

Previous or Next Displays the previous 20 or next 20 rules.

Common Rule Types

To create your own algorithms, use rules in the Einstein Recommendations Rule Manager tool.

Tip: Rules can override top performing algorithms and can have a negative impact on predictive performance. We recommend
applying them sparingly.

Scope Rule Syntax

Global Rule

Never recommend gift cards to customers. ACTION Exclude where <GiftCard> <is>
<Y>

Recommend highly rated items to users. ACTION Emphasize Items with <Ratings>
<Greater Than> <3>

Home Page Rule

Emphasize the newest items on the home ACTION Emphasize Items with
page. <ReleaseDate> <Less Than> <30> Days
Ago

Category Page Rules

Recommend only items with the same ACTION Include Items with <Category>
category as the landing page the subscriber <is> <Same as Reference Item>
views.

Detail Page Rule

345
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Scope Rule Syntax

Only recommend items of the same gender ACTION Include <Gender> <is> <Same as
as the item the subscriber views. Reference Item>

Only recommend Sale items when the ATTRIBUTE <isOnSale> <is> <False>
subscriber view a sale item.
ACTION Exclude <isOnSale> <is> <True>

Exclude items based on intended age group. ATTRIBUTE <AgeGroup> <is> <Child>

ACTION Exclude <Inappropriate> <is>

<True>

Exclude items based on intended age

group.

Do not recommend a competing brand on ATTRIBUTE <Brand> <is> <Nike>

a detail page.
ACTION Exclude <Brand> <is> <Adidas>

Only recommend items of the same brand ACTION Include <Brand> <is> <Same as
as the item that is being viewed. Reference Item>

Configure a Rule
Configure a rule to refine Einstein Recommendations.
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

1. Set Where to Apply the Rule

Determine where the rule is applied.
2. Set When to Apply the Rule
Determine which subscriber behaviors to apply the rule to.
3. Set How the Rule Is Applied
Determine how the rule is applied.
4. Choose How Rules Are Prioritized and Applied
After you configure rules for Einstein Recommendations in Einstein Recommendations, determine its priority when and where to
apply it.
5. Configure Advanced Rule Settings
Add advanced settings for the rule.
6. Validate the Rule Configuration
Confirm that the personalization for an Einstein Recommendation is configured correctly.

Set Where to Apply the Rule

Determine where the rule is applied.
1. Choose a catalog type to use.

346
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

2. Choose where to apply the rule.

You can drag-and-drop specific pages or email messages into the rule canvas to restrict application of the rule to those areas.

Note: As you configure your rule, the rule text section dynamically building a sentence to match the configuration.

Set When to Apply the Rule

Determine which subscriber behaviors to apply the rule to.
1. Select Events & Attributes.
2. Drag a Contact Event, Category, or Search parameter onto the rule canvas.
3. Select an operator.
4. Select an attribute type.
5. Select a value.
6. Drag an attribute into the rule canvas.
7. Select a tag field.
8. Select an operator.
9. Select a value.

Set How the Rule Is Applied

Determine how the rule is applied.
1. Select Actions.
2. Drag an action onto the rule canvas.
3. Select the catalog attribute to be acted upon.
4. Select the operator.
5. Select the catalog attribute value.
6. Select how much influence you want the rule to have on determining recommendations.

Choose How Rules Are Prioritized and Applied

After you configure rules for Einstein Recommendations in Einstein Recommendations, determine its priority when and where to apply
it.
Rule Manager Actions contain 6 options:

Operator Impact on Recommendations Example

Emphasize Increase the importance of a specific For web recommendations: When on the
attribute value. home page, emphasize items where
ReleaseDate occurs within the last 30 days.

Exclude Do not allow items with a specific attribute For email recommendations of any
value to be displayed. campaign: Exclude Items where
RegularPrice is less than $20.00.

347
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Operator Impact on Recommendations Example

Include Only display items with an attribute value For web recommendations: When on the
which matches the item being viewed. detail page Include Items where category is
same as reference item

Inject Manually force selected items to return For web recommendations: When on the
within the recommendations. cart page If BrandName is Northern Trails,
then inject BannerID
Northern-Trails-ShippingOffer.

Allow (only x) Limit the number of items that are returned For web recommendations: When on home
with a specific attribute value. page, allow only 2 Items where OnSale is
TRUE.

Allow (only x of any Limit the number of items with matching For web recommendations: When on any
attribute values that are returned. page and email recommendations of any
campaign allow only 2 items of the same
BrandName.

Configure advanced rule settings.

Configure Advanced Rule Settings

Add advanced settings for the rule.
1. To view the advanced settings section, click the gear icon.
2. If you do not want the rule to take effect immediately, set the Rule Start/Expiration Dates.
3. To chance the rule’s status, click Active/Inactive.
4. Click Save.

Validate the Rule Configuration

Confirm that the personalization for an Einstein Recommendation is configured correctly.
Review the Rule Text to verify that it is consistent with your expected result before saving each rule. To test the rule, make a
recommendation call and review the predictive content generated to verify that it meets your expectation.

Einstein Recommendation Scenarios

These scenarios help you produce Einstein Recommendations for email or the web in Marketing Cloud.

Tip: To apply custom logic to a scenario, use Rule Manager.

Reference Item Scenarios

These scenarios require one or more specific reference items. These items typically include a value passed in a SKU or CATEGORY parameter
via a recommendation call or email HTML content.

348
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Scenario Description Catalog Field Requirement Collect Field Requirement

Bought Bought Subscribers or visitors who SKU trackConversion
bought the item passed in the
parameter also bought these ProductCode
items.

Bought Bought Merge Subscribers or visitors who SKU trackCart

bought any of the items passed
in the parameter for this cart also ProductCode trackConversion
bought these items.

Click Bought Subscribers or visitors who SKU trackPageView

clicked the item passed in the
parameter also bought these ProductCode trackConversion
items.

Category Bought Subscribers or visitors who SKU trackPageView

viewed an item in the category
attribute passed in the ProductCode trackConversion
category= parameter also
bought these items.

Category View Subscribers and visitors who SKU trackPageView

viewed an item in the category
attribute passed in the ProductCode
category= parameter also ContentID
viewed these items.

Search Bought Subscribers or visitors who used SKU trackPageView

the search term passed in a
search= parameter bought ProductCode trackConversion
these items.

Search View Subscribers or visitors who used SKU trackPageView

the search term passed in a
search= parameter viewed ProductCode
these items. ContentID

Tag The most popular item based on SKU trackPageView

purchases, clicks, or views with
the attribute passed in the ProductCode
category= parameter. When ContentID
no attribute is passed, but the Attribute
item parameter is included,
the system chooses a reference
item tag value at random.

Tag Intersection Most popular items with an SKU trackPageView

intersection of attributes that
match the attributes of the ProductCode
parameter value for the item ContentID

349
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Scenario Description Catalog Field Requirement Collect Field Requirement

viewed by the subscriber or Attribute
visitor.

Tag Recent Newly available items with the SKU trackPageView

attribute passed in the
category= parameter. When ProductCode
no attribute is passed, but the ContentID
item parameter is included,
Attribute
the system chooses a reference
item tag value at random. Release Date

Tag Enjoyed Most viewed and purchased SKU trackPageView

items with the attribute passed
in the category= parameter. ProductCode trackCart
When no attribute is passed, the ContentID trackConversion
system chooses a reference item Attribute
tag value at random. Use at least
one Collect field.

Tag Top Rated Top rated item with the attribute ContentID trackPageView
passed in the category=
parameter. When no attribute is Attribute
passed, the system chooses a Rating
reference item tag value at
random.

View Bought Subscribers or visitors who SKU trackPageView

viewed the item passed in the
parameter also bought these ProductCode trackConversion
items.

View View Subscribers or visitors who SKU trackPageView

viewed the item passed in the
parameter also viewed these ProductCode
items. ContentID

View View Merge Subscribers or visitors who SKU trackPageView

viewed any of the items passed
in the parameter for this cart also ProductCode trackCart
viewed these items.

User Data Scenarios

These scenarios are based on a user’s Predictive Intelligence profile and personal site behavior.

350
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Scenario Description Catalog Field Requirement Collect Field Requirement

Bought Bought Last Cart Subscribers or visitors who SKU trackCart
bought the last item added to
the cart also bought these items. ProductCode trackConversion

Bought Bought Last Purchase Subscribers or visitors who SKU trackConversion

bought the item last purchased
also bought these items. ProductCode

Favorite Tag Most popular items with SKU trackPageView

attributes that match the
subscriber’s or visitor’s interest ProductCode
based on their affinity profile. ContentID
These recommendations are Attributes
based on the user’s top affinity.
Returns the most popular items
that match the single top tag on
their weighted affinity graph.

Last Views Merge Subscribers or visitors who SKU trackPageView

viewed any of the last 7 items
viewed by this subscriber or ProductCode
visitor also viewed these items. ContentID

Recently Viewed Any of the last 7 items viewed SKU trackPageView

by the subscriber or visitor.
ProductCode
ContentID

User Affinities Recommendations based on the SKU trackPageView

user’s complete affinity profile.
Returns items that match the ProductCode
top five affinities listed in their ContentID
contact profile, based on Attributes
purchases, clicks, and views over
time. Preference is given to
items that are tagged with
multiple attributes on the top
five affinity list.

View Bought Last Cart Subscribers or visitors who SKU trackPageView

viewed this item in a cart also
bought these items. ProductCode trackCart
trackConversion

View Bought Last Purchase Subscribers or visitors who SKU trackPageView

viewed the item last purchased
by this subscriber or visitor also ProductCode trackConversion
bought these items.

351
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Scenario Description Catalog Field Requirement Collect Field Requirement

View View Last Cart Subscribers or visitors who SKU trackPageView
viewed this item in the cart also
viewed these items. ProductCode trackCart

View View Last Purchase Subscribers or visitors who SKU trackPageView

viewed the item last purchased
by the subscriber or visitor also ProductCode trackConversion
viewed these items.

Site Data Scenarios

These scenarios are based on the collected aggregated site behavior. No information is personalized at the user level.

Scenario Description Catalog Field Requirement Collect Field Requirement

New Releases This information includes 100 SKU trackPageView
items across the site where the
ReleaseDate parameter is in the ProductCode
past 14 days. The values are ContentID
sorted by newest date. ReleaseDate

Top Enjoyed Most popular products across SKU trackPageView

the site based on a combination
of viewed and purchased items. ProductCode trackCart
ContentID trackConversion
Attribute

Top Grossing Highest grossing items in terms SKU trackConversion

of total revenue generated.
ProductCode

Top Sellers Top selling products across the SKU trackConversion

site based on units sold.
ProductCode

Top Views Up to 100 of the most viewed SKU trackPageView

items across the site.
ProductCode
ContentID

37

37
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

352
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Waterfall Predictions
When you enable waterfall predictions in Einstein Recommendations, the system begins with your top priority scenario and continues
down the list to your lowest priority scenario. At each step, it returns all available matching items until it reaches the total number of
recommendations you set.

Example: You set the recommendation number to four items. However, your top priority scenario only returns one
recommendation. The system moves to the next scenario on the list, and then the next, adding recommendations until there is
a total of four recommended items.

Note: If you choose not to enable Waterfall Predictions, the system only returns recommendations from the first algorithm
that provides the total number of recommendations you set.

Localized Recommendations
Configure Einstein Recommendations to deliver localized recommendations in multiple languages and currency values from a single
business unit.
Localized fields are only accessible through parameters added to recommendation calls.

Localized Catalog Requirements

Add customized fields to your catalog data extension to deliver localized recommendations through Einstein Recommendations.
Include a corresponding localized field for each language to support for all display fields in your catalog. Add the five-character locale
value to each localized field. Visit https://www.loc.gov/standards/iso639-2/php/code_list.php for examples.
To display localized pricing, include these fields in your product catalog.
• RegularPrice: This field only accepts a number value formatted for US dollars. Use this field to set rules in Rule Manager.
• RegularPriceDisplay: Add this attribute field and configure it to accept string values.
• SalePrice: This field only accepts a number value formatted for US dollars. Use this field to set rules in Rule Manager.
• SalePriceDisplay: Add this attribute field and configure it to accept string values.

Example:
SkuID|ProductCode|ProductName|locale_fr-FR_ProductName|locale_en-US_ProductName|Keywords|ProductLink|locale_fr-FR_ProductLink|locale_en-US_ProductLink|ImageLink|RegularPrice|SalePrice|OnlineAvailability|RegularPriceDisplay|locale_fr-FR_RegularPriceDisplay|locale_en-US_RegularPriceDisplay|SalePriceDisplay|locale_fr-FR_SalePriceDisplay|locale_en-US_SalePriceDisplay

Localized Email Recommendation Displays

To create recommendation displays with localized pricing, use the RegularPriceDisplay and SalePriceDisplay attributes
to ensure that the system displays correctly formatted pricing information.

Localized Email Recommendation Calls

To return localized recommendations, append the locale parameter to the email link. Match the locale parameter to the five-character
values used in the catalog field names.

Tip: Use all lowercase for locale= values in email recommendations.

353
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Example:
<a href=https://MID.recs.igodigital.com/rr/v2/hash/1/l/EMAIL?locale=fr-fr”>
<img src=https://MID.recs.igodigital.com/rr/v2/hash/i/1/EMAIL?locale=fr-fr” />
</a>

Localized Web Recommendation Calls

The system returns the localized display field when a web recommendation call is made when you append the locale parameter. Match
the locale parameter to the five-character value used in your catalog field names.

Example: To display a page localized for a french speaker in France, add locale=fr-FR.

Example: https://MID.recs.igodigital.com/a/v2/MID/PAGE/recommend.json?locale=fr-FR

Einstein Recommendations Reports

Learn about reports available in Einstein Recommendations.

Note: Execute Einstein Recommendations reporting at the page or campaign and scenario logic level. The custom querying and
large data sets for user and SKU or attribute level reporting must be scoped separately and can require a one-time or term services
engagement.

Site Metrics Influenced Metrics Recommendation Direct Metrics

Calculated from sessions during which a Calculated from items sold when a
subscriber clicked an Einstein subscriber clicked an Einstein
Recommendation. Recommendation and made a purchase
within the same session.

• Visits (Sessions) • Influenced Sessions • Direct Orders

• Orders • Influenced Orders • Direct Items Sold
• Items Sold • Influenced Revenue • Direct Revenue
• Revenue • Influenced Conversion Rate • Revenue per Thousand Impression
• Conversion Rate • Influenced AoV
• AoV • Influenced Revenue per Session
• Revenue per Session • Recommendation Displays
• Impressions • Recommendation Clicks
• Impressions per Visit

Dashboard Tabs
Learn about the dashboard tabs in Einstein Recommendations reports.
Einstein Recommendations Report Fields
See a list and description of all fields in Einstein Recommendations reports.
Einstein Recommendations Reports FAQs
Get the answers to frequently asked questions about Einstein Recommendations reports.

354
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Dashboard Tabs
Learn about the dashboard tabs in Einstein Recommendations reports.

Tab Description
Summary Provides a high-level view of Einstein Recommendations for email
and the web. You can select the time frame, view the data as a
graph, and choose the export format.

Recs and Recs by Scenario Web recommendation metrics by page and scenario

Email Email recommendation metrics separated by marketing campaigns

and triggered campaigns, and by hash code and scenario

Site Details Full site tracking data by day, including Einstein Recommendations
influenced and direct metrics

Contacts Search for subscribers by email address. View user profile data
including affinities, past activity, and current cart items. View affinity
attributes and weights for a specific user. If you implemented
Collect Tracking Code, you can also use this data by querying the
PI_PROFILES data table.
• Subscriber top 5 affinity values are shown in the table on the
right. These affinities are also held in the profiles data extension
when Collect Tracking Code data is integrated for your account.
• Left table shows the importance of attributes to the subscriber’s
site decisions.
• Affinities are created through combined purchases, clicks, and
views.

Admin Tools View data for products and lists used within Einstein
Recommendations.
Search by SKU or ProductCode to:
• Show all the item properties reflected by the most current
Catalog update.
• Manually mark an item out of stock. The Catalog Online
Availability field overwrites this value with the next catalog
import.
• View algorithm lists the item is included in.
Search for lists by typing in part of the corresponding scenario logic
name, like ‘new’ or ‘boughtbought’.
• Einstein Recommendations uses list data connected to each
scenario when determining which item to recommend
• Search for scenario list and view all current items on that list
• Weight represents the item’s overall enjoyment score, which
is calculated based on purchases, clicks, and views

355
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Displays by Item Report

Retrieve a report in Einstein Recommendations that displays the number of email recommendations by product code. This report
is accessible through the email tab in Email Recommendations reporting.

Displays by Item Report

Retrieve a report in Einstein Recommendations that displays the number of email recommendations by product code. This report is
accessible through the email tab in Email Recommendations reporting.
This report lists each product code, and the number of the times the product was recommended for each email recommendation
configuration and job ID. You can select a data range to view. To associate the job ID and recommendation, the email recommendation
image must include a URL parameter named sfmc_j with the email job ID as the value.
Follow these steps to enable tracking for this report.
1. In Einstein Recommendations, navigate to the Admin tab and click Implementation.
2. Scroll to the bottom of the page.
3. Select Activate Email Logging.

Note: Allow 24 hours for the system to collect data for this report.

Einstein Recommendations Report Fields

See a list and description of all fields in Einstein Recommendations reports.

Einstein Email Recommendation Report Fields

Tip: We recommend testing in a non-production business unit because measures can’t be reset.

Email Measure Description

Influenced Attribution The total revenue generated during sessions initiated by a
subscriber clicking a recommendation or reference item in triggers.
This value includes Direct Item Revenue.

Direct Attribution Number of orders with 7 days of a user click that contain a
recommended item or reference item trigger.

Displays The number of times recommendations are displayed. Tracked by

the number of times the recommendation call is made on a website
or the first recommendation image renders in an email.

Clicks The number of clicked recommendations or reference items in

triggers.

Click Rate The percentage of recommendations clicked. This value is

comparable to the click-to-open rate for email.

Direct Items The number of items sold within 7 days of a subscriber clicking a
recommendation or reference item in triggers.

Buy Rate The number of direct items sold over the total number of
recommendations.

356
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Email Measure Description

Site Lift This percentage represents the impact of predictive
recommendations on the site as a whole. It’s calculated by taking
the percentage increase from the non-influenced conversion rate
to the total conversion rate.

Influenced Revenue Total revenue generated during sessions initiated when a subscriber
clicks a recommendation or reference item in triggers. This figure
includes Direct Item Revenue.

Direct Item Revenue Total revenue from conversions within 7 days of a subscriber
clicking a recommendation or reference item in triggers.

Einstein Web Recommendation Report Fields

Web Measure Description

Visits The number of user sessions.

Items Sold The number of items purchased through the website.

Direct Order Revenue Total revenue for purchases that occur within 7 days of a clicked
recommendation or reference item in triggers.

Average Order Value Average value of orders placed.

Direct Item Revenue Total revenue from conversions that occur within 7 days of a
subscriber's clicking a recommendation or reference item in
triggers.

Influenced Revenue Percentage Percentage of revenue generated during sessions initiated by a

subscriber clicking a recommendation. This value includes Direct
Item Revenue.

Influenced Visits Number of visits initiated by a subscriber clicking a

recommendation that results in a purchase during the same
session. This value includes Direct Item Revenue.

Direct Items Revenue from customers who clicked a product recommendation

and purchased it in the same session.

Impressions Length of time a recommendation is displayed.

Average Order Value Lift This percentage represents the impact of predictive
recommendations on the orders placed on the site. It’s calculated
by taking the percentage increase from the non-influenced orders
to the overall order value.

Performance A listing of performance broken out by month.

Visits with Orders Number of visits resulting in a purchase.

Revenue Total revenue from all purchases.

357
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Web Measure Description

Impressions per Visit Average number of times recommendations are displayed per visit.

Conversion Rate The percentage of clicked recommendations that result in a

purchase within 7 days.

Direct Orders Number of orders with 7 days of a user click that contain a
recommended item or reference item trigger.

Influenced Revenue Total revenue generated during sessions initiated when a subscriber
clicks a recommendation or reference item in triggers. This figure
includes Direct Item Revenue.

Revenue per Session Average revenue per session.

Conversion Rate Lift This percentage represents the impact of predictive

recommendations on the site as a whole. It’s calculated by taking
the percentage increase from the non-influenced conversion rate
to the total conversion rate

Influenced Orders Total orders with revenue generated during sessions initiated by
a subscriber's clicking a recommendation or reference item in
triggers. This value includes Direct Item Revenue.

Revenue per Session Lift This percentage represents the overall impact of predictive
recommendations on revenue. It shows the percentage increase
from the non-influenced revenue per session to the total revenue
per session.

Direct Revenue Percentage The percentage of revenue within 7 days of a user's clicking a
recommendation or reference item in triggers.

Note: Web session ends when a visitor leaves the site or is inactive for a period determined by the account setup. The default is
60 minutes. Email attribution session is 7 days after the last click.

Einstein Recommendations Reports FAQs

Get the answers to frequently asked questions about Einstein Recommendations reports.

Where Does Einstein Recommendations Reporting Come From?

Reporting shown in the Einstein Recommendations dashboard comes from the Collect Tracking Code on the account’s site. For
example, revenue captured at the time of conversion is dependent upon what is passed through Collect Tracking Code rather than
pricing in the catalog.
What Is the Site Session Time Used in Einstein Recommendations Reporting? Can I Change This Setting?
You can configure the site session time inside the application under the gear icon in the Admin section. The default session time is
15 minutes. You can adjust it by 15-minute increments up to 3 hours.
What Time Zone Is Used for Einstein Recommendations Reporting?
Einstein Recommendations reporting uses Coordinated Universal Time (UTC). For this reason, orders and metrics from a single date
might not match when compared with data from other tracking systems.

358
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

Are Recommendation Displays Calculated at the Item or Call Level?

Recommendation displays are calculated at the call level. A single display is tracked, despite the number of recommended items
shown. When the recommendation call is made, the first image renders, or through a Collect Tracking Code or event triggers.
Is the Revenue Shown for Web Recommendations by Page Influenced or Direct Conversion?
Data for revenue broken down by page includes direct conversion. Influenced data cannot be attributed to a single web
recommendations page. The summary tab displays influenced web revenue at the site level.
How Do You Calculate the Site Lift Percentages Found on the Summary Tab in Einstein Recommendations?
Site lift is the percentage increase from the non-influenced number to the total number. Site lift for conversion rate and revenue per
session are shown on the Summary tab. This visualization helps represent the lift that Marketing Cloud Einstein Recommendations
provides to the overall site performance and is best analyzed trending over time.
How Do You Calculate the Comparison Percentages Found on the Summary Tab?
Comparison is the percent increase from the non-influenced number to the influenced number. The summary tab displays comparison
calculations for conversion rate and revenue per session.

Where Does Einstein Recommendations Reporting Come From?

Reporting shown in the Einstein Recommendations dashboard comes from the Collect Tracking Code on the account’s site. For example,
revenue captured at the time of conversion is dependent upon what is passed through Collect Tracking Code rather than pricing in the
catalog.

What Is the Site Session Time Used in Einstein Recommendations Reporting? Can I Change This Setting?
You can configure the site session time inside the application under the gear icon in the Admin section. The default session time is 15
minutes. You can adjust it by 15-minute increments up to 3 hours.

What Time Zone Is Used for Einstein Recommendations Reporting?

Einstein Recommendations reporting uses Coordinated Universal Time (UTC). For this reason, orders and metrics from a single date
might not match when compared with data from other tracking systems.

Are Recommendation Displays Calculated at the Item or Call Level?

Recommendation displays are calculated at the call level. A single display is tracked, despite the number of recommended items shown.
When the recommendation call is made, the first image renders, or through a Collect Tracking Code or event triggers.

Is the Revenue Shown for Web Recommendations by Page Influenced or Direct Conversion?
Data for revenue broken down by page includes direct conversion. Influenced data cannot be attributed to a single web recommendations
page. The summary tab displays influenced web revenue at the site level.

How Do You Calculate the Site Lift Percentages Found on the Summary Tab in Einstein Recommendations?
Site lift is the percentage increase from the non-influenced number to the total number. Site lift for conversion rate and revenue per
session are shown on the Summary tab. This visualization helps represent the lift that Marketing Cloud Einstein Recommendations
provides to the overall site performance and is best analyzed trending over time.

359
Marketing Cloud Einstein and Analytics Einstein Email Recommendations

How Do You Calculate the Comparison Percentages Found on the Summary Tab?
Comparison is the percent increase from the non-influenced number to the influenced number. The summary tab displays comparison
calculations for conversion rate and revenue per session.

Einstein Recommendations FAQs

Get the answers to frequently asked questions about Einstein Recommendations.

Can I Execute an Abandoned Cart or Abandoned Browse Email by Querying Einstein Recommendations Data Extensions?
Use Behavioral Triggers to create a list used in a send or journey.
If We Have Not Activated an Entry Event, Why Am I Receiving a Triggered Send to My Email Address?
Einstein Recommendations sends an email at the address you provided for triggered send testing and the data filter is operating as
expected. We remove the data filter so that the emails send to all customers.
Can You Add Multiple Attributes from the Same Field, Such as When a Category Is Both Sandals or Leather Then Apply the Action?
Yes, you can add multiple attributes from a field.
Can You Apply a Rule Based on an Individual Profile, for Instance, When a Customer’s Purchase History Contains a Product with
Category of Couch, Exclude Products with a Category of Sofa?
Yes, you can configure a rule to apply based on customer attributes.
Can You Specify Certain Scenarios a Rule Must Be Applied To?
No, rules are applied at a page level or channel level.
Can Different Rules Be Applied to Each Zone on a Page with Multiple Zones?
No, rules are applied at the page or channel level.
What Impact Does Apple Safari Intelligent Tracking Prevention Have on Salesforce Marketing Cloud's Einstein Recommendations?
Apple's Intelligent Tracking Prevention is a WebKit feature that reduces cross-site tracking by limiting cookies and other website
data. This feature works for Safari web browser users. Due to the limited nature in which the Einstein Recommendation platform
uses cookies, Einstein Recommendations work as designed for Safari users. Some users have reported that they must disable Safari's
cross-site tracking feature to see the recommendations. If the recommendations are not appearing on your main page, try enabling
Safari’s Prevent cross-site tracking setting. The cross-tracking option is enabled by default.
Why Does the System Add WF to a Scenario Name in an Einstein Recommendations Report?
The letters WF in the scenario name indicates the first scenario used to produce recommendations on a page where waterfall
predictions are enabled.
Will My Recommendation Show Items That Were Already Purchased?
No, purchased items are excluded in your recommendations.

Can I Execute an Abandoned Cart or Abandoned Browse Email by Querying Einstein Recommendations
Data Extensions?
Use Behavioral Triggers to create a list used in a send or journey.

SEE ALSO:
Behavioral Triggers

360
Marketing Cloud Einstein and Analytics Einstein Email and Web Recommendations Model Card

If We Have Not Activated an Entry Event, Why Am I Receiving a Triggered Send to My Email Address?
Einstein Recommendations sends an email at the address you provided for triggered send testing and the data filter is operating as
expected. We remove the data filter so that the emails send to all customers.

Can You Add Multiple Attributes from the Same Field, Such as When a Category Is Both Sandals or Leather
Then Apply the Action?
Yes, you can add multiple attributes from a field.

Can You Apply a Rule Based on an Individual Profile, for Instance, When a Customer’s Purchase History
Contains a Product with Category of Couch, Exclude Products with a Category of Sofa?
Yes, you can configure a rule to apply based on customer attributes.

Can You Specify Certain Scenarios a Rule Must Be Applied To?

No, rules are applied at a page level or channel level.

Can Different Rules Be Applied to Each Zone on a Page with Multiple Zones?
No, rules are applied at the page or channel level.

What Impact Does Apple Safari Intelligent Tracking Prevention Have on Salesforce Marketing Cloud's Einstein
Recommendations?
Apple's Intelligent Tracking Prevention is a WebKit feature that reduces cross-site tracking by limiting cookies and other website data.
This feature works for Safari web browser users. Due to the limited nature in which the Einstein Recommendation platform uses cookies,
Einstein Recommendations work as designed for Safari users. Some users have reported that they must disable Safari's cross-site tracking
feature to see the recommendations. If the recommendations are not appearing on your main page, try enabling Safari’s Prevent
cross-site tracking setting. The cross-tracking option is enabled by default.

Why Does the System Add WF to a Scenario Name in an Einstein Recommendations Report?
The letters WF in the scenario name indicates the first scenario used to produce recommendations on a page where waterfall predictions
are enabled.

Will My Recommendation Show Items That Were Already Purchased?

No, purchased items are excluded in your recommendations.

Einstein Email and Web Recommendations Model Card

The model in this card analyzes and provides personalized product and content recommendations.

Model Details
The Marketing Cloud Einstein Email and Web Recommendations model personalizes recommendations with training algorithms,
parameters, fairness constraints, features, and other applied approaches.
Intended Use
The Marketing Cloud Einstein Email and Web Recommendations model is intended for these use cases.

361
Marketing Cloud Einstein and Analytics Einstein Email and Web Recommendations Model Card

Relevant Factors
These factors are associated with the Marketing Cloud Einstein Email and Web Recommendations model.
Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance
measures are associated with the Marketing Cloud Einstein Email and Web Recommendations model.
Training Data
You have a customized version of the model that’s trained on your data alone. Data from one Salesforce customer doesn’t affect the
behavior for another Salesforce customer. While model training happens for each customer on their data, the initial development
of the model is validated with a representative set of pilot customers’ data.
Ethical Considerations
Review the ethical factors associated with the Marketing Cloud Einstein Email and Web Recommendations model. To avoid bias and
other ethical risks, the Einstein Email and Web Recommendations model doesn’t include demographic data.

Model Details
The Marketing Cloud Einstein Email and Web Recommendations model personalizes recommendations with training algorithms,
parameters, fairness constraints, features, and other applied approaches.

Person or Organization
Salesforce Marketing Cloud Einstein

Model Date and Version

• December 2021
• Minor changes can occur throughout the release
• Major changes can occur and are communicated via release notes

Model Type
Clustering

General Information
The Einstein model powering Einstein Email and Web Recommendations uses customer data provided by Collect Tracking Code on
page 50 API, and the Einstein Recommendations Catalog on page 318.

License
Email Recommendations is available to Salesforce Marketing Cloud customers with any of these editions.
• Professional Edition (Email Recommendations only)
• Corporate Edition
• Enterprise Edition
• Enterprise+ Edition

362
Marketing Cloud Einstein and Analytics Einstein Email and Web Recommendations Model Card

Questions or Comments
Send questions or comments about the model to mce-support@salesforce.com.

Intended Use
The Marketing Cloud Einstein Email and Web Recommendations model is intended for these use cases.

Primary Intended Uses

Einstein Recommendations provides personalize product and content recommendations to help drive revenue on email, web, and other
marketing channels including these options.
• People Who Bought This Also Bought
• People Who Bought This Also Viewed
• People Who Viewed This Also Bought
• People Who Viewed This Also Viewed
• User Affinity
• Tag Scenarios

Note: See the full list of Einstein Recommendation Scenarios on page 348.

Out-of-Scope Use Cases

Anything other than the primary use case is out of scope and not recommended.

Relevant Factors
These factors are associated with the Marketing Cloud Einstein Email and Web Recommendations model.

Model Input
Einstein Recommendations analyzes up to 180 days of historical behavioral data from Collect.js for each business unit. The engagement
history includes these factors.
• Pageviews
• Category Views
• Carts
• Conversions
• Wishlists
• Metadata from the product or content catalog used to build user affinity and provide attribute context. The affinity profile is created
from user-tagged metadata from the catalog and is based on behavioral information.
• Output is based on localized behavioral data, catalog content, and user attributes by business unit.
• Business-specific rules added using Rule Manager on page 344 impact the model
The engagement history that Einstein Probabilistic Open analyzes excludes these factors.
• Data purchased or collected from third parties
• Data from other business units

363
Marketing Cloud Einstein and Analytics Einstein Web Recommendations

• Demographic Data, which is typically stored in SFMC as data extensions or subscriber or contact attributes

Model Output
• The model output is a list of products or content via email or web recommendation call
• Web recommendation output is a JSON block
• Email Recommendation is a link & image pair

Environment
The model is trained and deployed in the Salesforce Marketing Cloud environment.

Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance measures
are associated with the Marketing Cloud Einstein Email and Web Recommendations model.

Model Performance Measures

Model performance metrics include data like model mean absolute error score.

Training Data
You have a customized version of the model that’s trained on your data alone. Data from one Salesforce customer doesn’t affect the
behavior for another Salesforce customer. While model training happens for each customer on their data, the initial development of the
model is validated with a representative set of pilot customers’ data.

Ethical Considerations
Review the ethical factors associated with the Marketing Cloud Einstein Email and Web Recommendations model. To avoid bias and
other ethical risks, the Einstein Email and Web Recommendations model doesn’t include demographic data.
Consider any assumptions made when deciding on actions based on the model-generated scores that could lead to a potentially adverse
outcome.

Example: For example, the model predicts low engagement so you choose not to send a marketing communication to a set of
customers. If the prediction was erroneous, there could be negative impact to excluding some of those customers from access to
benefits or opportunities.

Einstein Web Recommendations

Einstein Web Recommendations use Einstein's capabilities to observe behavior, build preference profiles, and deliver the next-best
personalized content to each website visitor. Use scenarios within the application to refine recommendations to match your specific
business rules. Predictive Content is surfaced in placeholders for recommendations on your website.
Web Recommendations are delivered in two ways, via a JSON response or HTML/JS. The JSON response is the best practice delivery
method unless their web team cannot work with JSON. The JSON method is the most flexible and allows their web team to style and
utilize the recommendation data in any way. Because of the nature of the web recommendation and the JSON response, you are
responsible for parsing and styling the recommendation within their web environment.
Here is an example of the response for a web recommendation:

364
Marketing Cloud Einstein and Analytics Einstein Web Recommendations

You can pull any catalog field into the web recommendation call, so it is vital to understand what data generates the recommendation
during the catalog setup.
A unique web recommendation call is created for each type of page. We recommend that you include Home, Product, Category, Cart,
and Conversion pages as a best practice. However, there is no limit to the number of pages that can be set up in the UI. Einstein
Recommendations uses page templates, so a Product Page is a template used to build personalized recommendations for a product
page.
Each type of page template can have different scenarios and a different context. For example, your product page can include
recommendations based on the product a visitor is viewing based on that added context. However, your homepage recommendations
are based on the overall user affinity because we don’t have more context.
If you have a service engagement, the State of Work sets the number of pages services configures. However, you can add as many as
you need.
38

Einstein Web Recommendation Dashboard

The web recommendation dashboard in Einstein Recommendations displays a list of available recommendations. From here, you
can edit or delete a recommendation or create a new one.
Create an Einstein Web Recommendation
Use Marketing Cloud Einstein Recommendations to create product or content recommendations to display on your website. The
Einstein Recommendation Engine requires at least three active items in your product catalog.

Einstein Web Recommendation Dashboard

The web recommendation dashboard in Einstein Recommendations displays a list of available recommendations. From here, you can
edit or delete a recommendation or create a new one.
The dashboard is the first screen you see when you open Einstein Web Recommendations. Click the Overview tab to return to the
dashboard.

38
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

365
Marketing Cloud Einstein and Analytics Einstein Web Recommendations

Column Header Description

Page Name of the page which is used for reporting. The name cannot
be changed once it is created. We recommend that the page name
matches the page template on your site for consistency.

Type Lists the type of recommendations to be made: Product, Content,

or Banner. More than one type can be displayed for sites with more
than one active catalog.

Areas Name for the location on the page where recommendations are
displayed. More than one area can be displayed here since a page
can have more than one recommendation zone.

Tip: Use the column headers or arrowheads within the column to sort.

Create an Einstein Web Recommendation

Use Marketing Cloud Einstein Recommendations to create product or content recommendations to display on your website. The Einstein
Recommendation Engine requires at least three active items in your product catalog.

Note: When your customer profile privacy field is set to one of the following, the system generates generic recommendations
from the scenarios you configured.
• Do Not Track
• Do Not Profile
• Do Not Process
For example, you configure View as the top scenario. The customer who views a product detail page sees recommendations for
products that other customers also viewed.

366
Marketing Cloud Einstein and Analytics Einstein Web Recommendations

Tip: System Scenarios are enabled by default and provide filler content when configured scenarios do not produce the expected
number of recommendations. To disable this feature, select Disable System Scenarios box.
39

1. Set the Location and Type of Web Recommendation

Configure where Einstein Web Recommendations appear on your site and the type of recommendations to provide.
2. Create the Einstein Web Recommendations Content Area
Select and configure the content to include in your web recommendations.
3. Configure the Web Recommendations Display Format
Format how your recommendations appear on your website.
4. Configure the Einstein Web Recommendations Scenario
Determine which recommendation scenarios to use in Einstein Web Recommendations.
5. Preview and Insert Einstein Web Recommendations
Include the Einstein Web Recommendations code in the selected page’s code. Both the JavaScript for the recommendation call and
the HTML recommendation zone placeholder are provided.

Set the Location and Type of Web Recommendation

Configure where Einstein Web Recommendations appear on your site and the type of recommendations to provide.
1. Navigate to Einstein and select Einstein Web Recommendations.
2. To create a page, click Create New Page and enter a page name. To use an existing page, select a page from the list.

Note: The page name can’t include spaces. Standard page names are Home, Cart, Product, Search, and Category. If you
attempt to create a page using the same name as an existing page, the new page is not created.

3. Choose the recommendation type from the list.

4. Click Create.
The Build tab opens with a recommendation area with the default name igdrec_1.

Create the Einstein Web Recommendations Content Area

Select and configure the content to include in your web recommendations.
1. Click the name igdrec_1 and enter a new name.
2. Choose Number or Range from the dropdown.
3. Enter the number, or select the range, of recommendations to return.
To preview your recommendation, click Preview.

Tip: If there are not enough items available for recommendations, nothing is returned unless you select Waterfall Predictions.

4. To add more recommendation areas to this page, click Add Another Area and repeat steps 1–4.
5. Click Save.
The Build tab closes and returns you to the web personalization dashboard. The new page is listed.

39
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

367
Marketing Cloud Einstein and Analytics Einstein Web Recommendations

Configure the Web Recommendations Display Format

Format how your recommendations appear on your website.
1. Select the page to be modified and click the Output tab.

Note: The canvas displays previously chosen output fields for the page. If nothing is chosen, the system generates recommended
output fields based on your catalog fields.

2. Choose the output preview format.

3. Select a field to display from the list and click Add.
4. To add more fields, repeat the previous step.
5. To change the display fields order, drag the fields into order from top to bottom on the canvas.

Note: To delete a field, click .

The Output Preview displays the output code.
6. To see how the code renders, click Preview.
To return to the canvas, click Close.

7. Click Save.

Configure the Einstein Web Recommendations Scenario

Determine which recommendation scenarios to use in Einstein Web Recommendations.
1. Click the recommendation to configure.
2. Click the Scenarios tab.
3. Select a scenario and click Add.

Note: For details about what each scenario does, see Einstein Recommendation Scenarios.

The scenario appears on the canvas. It is automatically set to apply to all recommendation areas.
4. Click all areas and select a specific recommendation area.
5. To add more scenarios, repeat steps 3 and 4.

Tip: To remove a scenario from the canvas, click .

Tip: Personalization Builder returns predictions from the top ranked scenario.

6. To reorder the priority of scenarios, drag them into the order from top to bottom.
7. To use waterfall predictions, select Enable Waterfall Prediction.

Tip: Learn more about Waterfall Predictions.

8. To suppress system-generated scenarios, select Disable System Scenarios.

9. Click Save.

Note: To restore the default scenario configuration, click Restore to Default Best Practices and click Save.

368
Marketing Cloud Einstein and Analytics Einstein Web Recommendations

40

Preview and Insert Einstein Web Recommendations

Include the Einstein Web Recommendations code in the selected page’s code. Both the JavaScript for the recommendation call and the
HTML recommendation zone placeholder are provided.
1. To insert the code, click the Get Code tab.
2. Copy the code.
For more information and to learn how to customize the code, review Get Code Details and Customize the Calls.

3. Place the code into your website code.

41

Get Code Procedures

Learn how to add the Einstein Web Recommendations code you create in Einstein Recommendations to your website.

Get Code Procedures

Learn how to add the Einstein Web Recommendations code you create in Einstein Recommendations to your website.

Note: Basic HTML and CSS skills are required to complete this process.

1. Select a page from the Web Recommendation dashboard.

2. Click the Get Code tab.
3. Copy each piece of code and embed it in the page code .
For more information on embedding the code and customizing calls, review Get Code Details in Personalization Builder and Customize
the Calls.

Tip: After the code is applied to your webpages, the recommendations are live. We recommend that you test recommendations
to a test environment before you add them to a live site.
42

Get Code Details in Einstein Recommendations

Find the JavaScript and HTML code required to render Einstein Recommendations on your page. Copy the code and embed it in
your page source for each piece of code.
Customize the Calls
Marketing Cloud Einstein Recommendations code accepts several different parameters. To initiate an API call, use HTTP or HTTPS to
match the address prefix of the page on your site where the call is made.

Get Code Details in Einstein Recommendations

Find the JavaScript and HTML code required to render Einstein Recommendations on your page. Copy the code and embed it in your
page source for each piece of code.

40
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.
41
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.
42
Rights of ALBERT EINSTEIN are used with permission of The Hebrew University of Jerusalem. Represented exclusively by Greenlight.

369
Marketing Cloud Einstein and Analytics Einstein Web Recommendations

Customize the provided basic recommendation calls to match your site. The description key in each box shows additional information
that you can pass in the JavaScript source URL. Replace these client parameters in the base URL of the call with valid values.
• <client>
• <pagename>
These client parameters are not run-time variables. The variables after ? are supplied in the call at run time.
There are required fields for some pages.

Page Required Field

Product Detail ProductCode

Category CategoryName

Cart List of cart ProductCodes

Search Search Term

Example: Homepage
Place the div where it’s displayed in the recommendation. Place this value exactly where it appears on the page.
<div id=”igdrec_1”></div>.
Next, place a script tag with this code.
<script
src="http://<client_name>.recs.igodigital.com/a/v2/<client>/home/recommend.js"></script>

Example: Product Detail Page

Place the div where it’s displayed in the recommendation. Place this value exactly where it appears on the page.
<div id=”igdrec_1”></div>.
Next, place a script tag with this code.
<script
src="http://<client_name>.recs.igodigital.com/a/v2/<client>/product/recommend.js?item=ProductCode"></script>..

ProductCode is the item viewed and must match the same value passed in the Collect Tracking Code item variable.

Example: Category and Sub-Category Page

Place the div where the recommendation displays. Place this value exactly where it appears on the page.
<div id=”igdrec_1”></div>.
Next, place a script tag with this code.
<script
src="http://<client_name>.recs.igodigital.com/a/v2/<client>/category/recommend.js?
category=Category_name"></script>.
Replace Category with the actual category page name where the recommendation call is being made. This code must exactly
match the categories stored in the product catalog category.
If the category name includes any spaces or special characters, the URL value must be encoded. For example, if the category is
Category & Name, then the URL parameter is category=Category%20%26%20Name.

370
Marketing Cloud Einstein and Analytics Einstein Web Recommendations

Example: Shopping Cart Review Page

Place the div where the recommendation displays. Place this value exactly where it appears on the page.
<div id=”igdrec_1”></div>.
Place a script tag with this code after the div.
<script
src="https://<client_name>.recs.igodigital.com/a/<client>/cart/recommend.js?cart=ProductCode".</script>.
Match the value in ProductCode to the value sent in the Collect Tracking Code cart variable as a pipe-delimited list.

Customize the Calls

Marketing Cloud Einstein Recommendations code accepts several different parameters. To initiate an API call, use HTTP or HTTPS to
match the address prefix of the page on your site where the call is made.

Parameter Details
item This unique identifier for your product or content must match the
unique key in the catalog and the value sent in the trackPageView
collect item variable. This parameter is required to make a product-
or content-based recommendation on any page. The unique
identifier is the product code: item=XXXXXX, where XXXXXX is the
ProductCode.

search This pipe-delimited list contains search terms from your search
page and matches the value sent in the trackPageView collect
search variable.

category This pipe-delimited list of categories matches both the values sent
in the catalog feed and the value sent in the trackPageView collect
category variable.

cart This pipe-delimited list of products in the cart matches the trackCart
collect item variable.

wishlist This pipe-delimited list of products in the customer's wishlist must

match the trackWishlist collect items variable array.

email Use this parameter for faux-server-side, CloudPages, MobilePush,

FaceBook tab, or some mobile apps. Pass the email address of the
profile recommendation you want to access. The email value is
the same value passed to Collect. If this value is a SubscriberKey,
pass the SubscriberKey value.

user_id This parameter is used in testing or an advanced setup. It returns

the cookie value from the profile containing the recommendations
you want to access.

item_count Use this parameter to set the number of returned products or

override the returned products setting.

locale This five-character value indicates which localized content to

display.

371
Marketing Cloud Einstein and Analytics A Marketer's Guide to the Trusted Use of Einstein

Parameter Details
exclusion Use this parameter to pass a pipe-delimited list of key-value pairs
to exclude: field_name_1|field_value|field_name_2|field_value.

Table 12: Calls No Longer Supported

Parameter Details
cart_skus This pipe-delimited list of products in the cart matches the trackCart
collect unique_id variable.

with_root Deprecated in V2: When this parameter is set on a product or

content detail page, the first recommendation in each module is
the product or content the subscriber is accessing. The most
common use for this value would be a recommendation, such as
“People who bought <Root Product> also bought <with_root
recommendation>:”

do_not_record nolog This parameter instructs the system not to record the
recommendation.

inclusion Use this parameter to pass a list of product SKUs for inclusion.

A Marketer's Guide to the Trusted Use of Einstein

Salesforce believes that the benefits of AI can be accessible to everyone. But increasingly, AI is facing a crisis of trust.
In March 2021, a global survey found that citizens have low trust in AI systems but expect organizations to uphold the principles of
trustworthy AI, including inclusivity, transparency, and accountability. Fewer that half of customers, 48%, trust companies to use AI
ethically, and 65% are concerned about unethical AI use. The growing use of AI in marketing is complex, as many AI models are criticized
for lacking transparencey and accountability.
Einstein for Marketing makes a marketer's efforts more efficient while creating optimized and engaging one-on-one customer experiences
at scale. These AI-based services are powerful tools that help drive segmentation, content optimization and creation, automate orchestration
and provide insights to improve performance. Let's explore how you can ensure your Einstein-driven marketing is accurate and trustworthy.
Our Trusted and Transparent Approach
At Salesforce, we're committed to developing ethical and inclusive technology. Our Trusted AI Principles are Responsible, Accountable,
Transparent, Empowering, and Inclusive. The principles are built on Salesforce's core values of Trust, Customer Success, Innovation, and
Equality. As part of our commitment to ethical technology use, our Research & Insights team collaborated with our Marketing Cloud
product teams and the Office of Ethical and Humane Use to publish our Responsible Marketing Principles. The principles document
outlines some tools that we developed so that our employees, customers, and partners can use AI more responsibly, accurately, and
ethically.
Use Model Cards to Understand How Our Models Work
Consumers and marketers want to know how a model behaves and how it arrives at its prediction or recommendation in order to trust
the model. Marketing Cloud Einstein model cards provide critical information about model inputs and outputs, the conditions when
models work best, and the ethical considerations in their use. These cards answer questions about using the models as intended, and
whether there are any biases to consider. Providing this transparency helps developers, customers, policymakers, and others better
understand the impact of our AI on individuals, communities, and society. Check out these model cards for details.

372
Marketing Cloud Einstein and Analytics A Marketer's Guide to the Trusted Use of Einstein

• Einstein Send Time Optimization for Email on page 254 determines the optimal time to send an email to a subscriber to maximize
the probability that the subscriber opens the email.
• Einstein Send Time Optimization for Mobile on page 258 determines the optimal time to send a mobile message to maximize the
probability that a subscriber interacts with the message.
• Einstein Engagement Scores for Mobile on page 236 evaluates each contact's engagement record to assign scores for the contact's
likelihood to interact with mobile messaging.
• Einstein Messaging Insights on page 246 monitors message engagement rates and notifies marketers when anomalies in their
marketing performance occur.
• Einstein Engagement Frequency on page 265 analyzes each contact's engagement record to determine the optimal frequency at
which to send email messages to that contact.
• Einstein Subject Line Tester on page 273 evaluates contact engagement based on email subject lines.
Check Data Quality Scores to Ensure Your Data is AI-Ready
Use data quality scores as indicators to help you determine how ready your data is for Einstein to make accurate predictions. With any
AI model, the quality of the output depends on the quality, representativeness, and robustness of the input. Data quality scores show
you when the data is in good or bad shape, why it's in that shape, and general tips for improvement.
• Gauge Your Einstein Engagement Scoring Data Quality
• Gauge Your Einstein Engagement Frequency Data Quality
• Gauge Your Einstein Send Time Optimization Data Quality
Review Bias Flags to Prevent Potential Disparate Impact
Bias flags indicate when selected inputs can introduce bias into the model. For example, Einstein Content Selection uses bias flags to
indicate potentially sensitive attributes in profile data. And in Einstein Subject Line Tester, bias flags show when words or phrases in a
sample can be considered sensitive. Bias is contextual and based on industry and use cases. Einstein highlights potential bias so that
you can evaluate how to proceed based on the context.
• Identify Attributes That Can Introduce Bias
• Test a Subject Line Before You Send
Call to Action
To optimize your marketing efforts with Marketing Cloud, use these prompts toward deeper thought and discussion. The prompts aren't
exhaustive and don’t apply to all organizations, teams, products, or features.
• Are your training and evaluation datasets representative of your customer population? How do you know?
• Have you assessed your datasets and models for bias?
• If you have launch criteria, does your model meet that criteria for various population subgroups?
• Does your model have similar performance for the various population subgroups or does it perform worse for one group versus
another?
• Are you using AI to infer sensitive information about your users such as age, gender, health status, sexual orientation, political
affiliation, financial status, or criminal convictions?
• Are you collecting and using sensitive data only when necessary and when it can benefit the customer?
• Are you using sensitive data proxies such as first name or salutation that can relate to gender, or ZIP code that can relate to race,
unnecessarily?
• Are you giving customers control over the data that you collect and do you respect their preferences?
• Are you demonstrating the benefits that customers receive in exchange for data usage?
Summary

373
Marketing Cloud Einstein and Analytics Salesforce Audience Studio and Data Studio

The ethical use of AI is an increasingly complex issue to address to ensure that it's safe and inclusive for all. Model cards, data quality
scores, and bias flags are a few of the ways that we infuse ethics into our AI practices at Salesforce.
Resources
• Salesforce Responsible AI in Marketing
• Salesforce Responsible Creation of AI Trailhead
• Salesforce AI Ethics Blog
Join Us
If you're interested in participating in Salesforce User Research, sign up for our research program and influence product design and
direction. If you need more incentive, we almost always provide a thank you gift!
Contact Us
If you have questions about the ethical use of Marketing Cloud Einstein, contact your Salesforce account executive, or email
buildwithintention@salesforce.com. A team monitors this inbox and typically responds within 72 hours.

Salesforce Audience Studio and Data Studio

View Salesforce Audience Studio and Data Studio documentation.

Audience Studio
Salesforce allows you to capture, unify, and activate your data to strengthen consumer relationships across every touchpoint with
a powerful data management platform.
Data Studio
Data Studio, or data sharing, is Salesforce's #1 solution for audience discovery, data acquisition, and data provisioning — featuring
the world's largest premium data ecosystem.

Audience Studio
Salesforce allows you to capture, unify, and activate your data to strengthen consumer relationships across every touchpoint with a
powerful data management platform.
Salesforce Audience Studio lets you:
• Create complete data profiles - Combine all your data from any source to deliver more relevant marketing experience.
• Discover new insights - Respond to new data signals and sources to identify new audiences.
• Access premium data sources - Use the most trusted second- and third-party data sources to build and scale your audiences.
Visit Audience Studio Resources for more information.

Data Studio
Data Studio, or data sharing, is Salesforce's #1 solution for audience discovery, data acquisition, and data provisioning — featuring the
world's largest premium data ecosystem.
Data Studio lets you:
• Create richer audiences for Marketers - Discover high-quality audiences at scale.
• Increase revenue for data owners - Monetize your data with full transparency and control.

374
Marketing Cloud Einstein and Analytics Data Studio

• Take control of your data - Protect your data and provision it at scale to trusted partners with data governance.
Visit Data Studio FAQ for more information.

Note: Data Studio help articles are only available with a Audience Studio login.

375
INDEX

Google Analytics 360 198, 204–205

A GroupConnect 41
analytics 1, 3–8, 13, 16–19, 21, 23–39, 41–42, 44, 46–47, 191, 194–
197, 200–204, 210, 217, 222–227, 230, 232–236, 243 I
Analytics Builder
integration 191, 194, 196–197, 200–204
Einstein Engagement Frequency
262–264 J
Activate 263
Journey Builder 39, 196–200, 250
Audience Studio
Data Studio 374 M
C microsites 6–8
MobileConnect 46–47
CloudPages 7
MobilePush 42, 44
collect code 50–51, 53–59, 61–62
Collect Tracking Code 340, 343 N
Contact Builder 4–5
notifications 343
Content Builder 301–303
content tagging 302–303
customer profile 330, 340
P
Personalization Builder 307, 312, 328–330, 334–336, 340, 343,
D 345, 356, 359–361
privacy management 334–336
data extension 340
data extensions 340
R
E recommendations 304–309, 316–319, 322–327, 335–338, 341–
348, 353–356, 358, 360, 364–369, 371
Einstein 211–213, 215, 219, 221–227, 230, 232, 234–254, 257–
Reporting 8
262, 265–276, 296–298, 301–309, 316, 318–319, 322–327,
reports 13, 18, 48–50, 356
329–330, 335–338, 340–348, 353–356, 358–369, 371
Reports 3–8, 13, 16–19, 21, 23–39, 41–42, 44, 46–47
Einstein Engagement Scoring 233
Einsteing 367
Email Studio 13, 16–19, 21, 23–37
S
Send Time Optimization 250
F status console 343
faq 202–204, 243, 328–330, 359–361
FAQ 361
T
tags 301–302
G tracking beacon 50–51, 53–59, 61–62
Google Analytics 191, 194–197, 200–205

376