Fundamentals of Big

Data Analytics and BI

By Derbew Felasman(MSc)
Chapter One
Introduction to Big Data Analytics
What is Data?
● Data is factual information you can process for reasoning, discussion,
or calculation
● Information in raw or unorganized form
● Basis for information and knowledge
Sources of Data
Source of Data Description

Internal Sales, Customer, Financial, Operational,

HR, Inventory
External Government Databases, Industry Reports,
Market Research Firms, Social Media,
Web Scraping, IoT Devices, Public
Datasets
What makes the data big?
What is BigData?
★ Big data refers to large and complex data sets that are generated at
high speeds from various sources.
★ No typical data management systems can effectively store or analyze
this data because of its magnitude and complexity.
★ Forms the backbone of Big Data Analytics.
★ Used in fields like AI, IoT, and digital transformation.
Types of Big Data
★ Structured Data: Data that resides in fixed formats (e.g., relational
databases).
★ Semi-Structured Data: Data that doesn't conform to a traditional
database table but contains tags or a hierarchical structure (e.g., XML,
JSON).
★ Unstructured Data: Data that doesn't have a predefined data model or
organized structure (e.g., text, images, videos).
Characteristics of Big Data
Characteristics of Big Data
★ Volume: the massive amount of data generated and collected from
various sources.
★ Velocity: The speed at which data is generated and processed,
necessitating real-time analysis.
★ Variety: The diversity of data types and sources, including text, images,
videos, and more.
★ Veracity: The accuracy and reliability of the data collected, which
affects decision-making confidence.
★ Value: The potential insights that can be extracted from the data to
enhance business operations
Facebook stat
★ Facebook is the world’s third most-visited website with almost 3 billion monthly
active users.
★ Facebook users are still incredibly active with 510,000 comments posted,
293,000 statuses updated, 240,000 photos uploaded, 4 million likes every
minute.
★ Nearly 7 billion messages are sent every minute through Facebook’s family of
apps (including Messenger, Instagram, Whatsapp, etc.)
★ Users spend an average of 35 minutes every day on Facebook.
★ Facebook users click on an average of 12 ads every month.
Facebook
★ Facebook, one of the world's largest social media platforms, is a prime
example of a company that leverages Big Data to its advantage. Let's break
down how Facebook applies the 5 Vs of Big Data:
★ Volume:
○ Billions of Daily Users: Facebook processes billions of posts, comments,
likes, and shares daily.
○ Diverse Data Types: This includes text, images, videos, and location data.
Facebook
★ Velocity:
○ Real-Time Data: Facebook must process data in real-time to keep up with the
constant flow of user activity.
○ Rapid Updates: News feeds, trends, and ad targeting are updated in real-time.
★ Variety:
○ Diverse Data Sources: Data comes from various sources, including user
profiles, posts, comments, likes, shares, messages, and photos.
○ Structured and Unstructured Data: This includes both structured data (e.g., user
profiles) and unstructured data (e.g., text posts, images).
Facebook
★ Veracity:
○ Data Quality: Facebook must ensure the accuracy and reliability of the
data to make informed decisions.
○ Noise Reduction: Filtering out spam, fake accounts, and misinformation is
crucial.
★ Value:
○ Facebook uses data to tailor news feeds, ad recommendations, and friend
suggestions for each user.
○ Businesses can use Facebook's advertising platform to target specific
demographics and measure the effectiveness of their campaigns.
○ Product Improvement: Analyzing user behavior helps Facebook identify
areas for improvement in its products and features.
What are Big Data Analytics?
★ The process of examining large, varied data sets to uncover hidden
patterns, unknown correlations, market trends, customer preferences,
and other useful information.
★ Involves the use of advanced analytical techniques and tools.
★ Combines advanced analytics techniques like machine learning,
predictive modeling, and statistical methods.
Why We Need Big Data Analytics?
★ Improved Decision-Making
○ Empowers organizations to make informed, data-driven decisions.
○ Enhances strategic planning and operational efficiency.
★ Handling Data Explosion
○ Manages the ever-increasing volume of data generated from diverse
sources.
○ Processes complex datasets efficiently to derive actionable insights.
★ Enhancing Customer Experiences
Why We Need Big Data Analytics?
★ Predictive Insights
○ Anticipates future trends and outcomes using advanced analytics.
○ Assists in risk management, demand forecasting, and resource planning.
★ Operational Efficiency
○ Optimizes workflows, supply chains, and resource utilization.
○ Reduces costs and increases productivity with process automation.
★ Competitive Advantage
○ Helps businesses stay ahead by identifying opportunities and threats.
Why We Need Big Data Analytics?
★ Real-Time Decision Making
○ Facilitates instant responses to dynamic conditions using real-time
analytics.
○ Crucial for applications like fraud detection and IoT-driven operations.
★ Driving Innovation
○ Fuels advancements in AI, IoT, and smart technologies.
○ Encourages development of new products, services, and business
models.
Types of Big Data Analytics
★ Descriptive Analytics: Summarizes historical data to understand
what has happened. Answers "What happened?" and identifies
trends.
★ Example: Analyzing sales data to understand past performance.
○ Question: How many products did we sell last month?
○ Answer: A simple report showing the total number of products sold.
Types of Big Data Analytics
★ Diagnostic Analytics: Analyzes historical data to find the reasons
for outcomes. Answers "Why did it happen?"
★ Example: Investigating why sales decreased in a specific region.
○ Question: Why did sales in the Western region decline?
○ Answer: Analyzing factors like competitor activity, economic conditions, or
marketing campaigns in that region.
Types of Big Data Analytics
★ Predictive Analytics: Uses statistical models and machine
learning to forecast future outcomes. Answers "What is likely to
happen?"
★ Example: Forecasting future sales based on historical trends.
○ Question: What will our sales be next quarter?
○ Answer: Using statistical models to predict future sales based on past
data.
Types of Big Data Analytics
★ Prescriptive Analytics: Recommends actions to optimize
outcomes based on predictions. Answers "What should be
done?"
★ Example: Recommending marketing strategies to boost sales.
○ Question: What marketing campaign should we launch to increase sales?
○ Answer: Analyzing customer data to identify target segments and
recommending tailored marketing strategies.
Key Components of Big Data Analytics
★ Data Collection: Gathering data from various sources like IoT devices
and online platforms.
★ Data Preparation: Organizing, cleaning, and validating data for
analysis. Converts raw data into structured formats.
★ Data Analysis: Applying analytical tools to discover patterns and
insights.
★ Modeling and Visualization: Developing models and visualizing data
to communicate findings effectively.
Domain-Specific Examples of Big Data
Web and Social Media
★ User Behavior Analysis: Tracking user interactions on websites to understand
behavior patterns and improve user experience.
★ Personalized Recommendations: Analyzing user data to provide tailored
recommendations for products, content, and services.
★ Sentiment Analysis: Analyzing social media data to measure public opinion
and sentiment towards brands, products, or events.
Financial Sector
★ Fraud Detection: Analyzing transaction data to identify fraudulent
activities in real-time.
★ Risk Management: Assessing financial risks by analyzing market data,
customer data, and economic indicators.
★ Customer Segmentation: Grouping customers based on their financial
behavior to offer personalized services.
Healthcare
★ Hospitals: Improving patient outcomes by analyzing Electronic Health
Records(EHRs) to identify best practices and optimize treatment plans.
★ Pharmaceutical Companies: Conducting clinical trials and developing
new drugs based on large-scale data analysis.
★ Public Health Organizations: Predicting and preventing disease
outbreaks by analyzing population health data.
Internet of Things (IoT)
★ Manufacturing: Optimizing production processes and reducing
downtime by analyzing sensor data from machinery.
★ Transportation: Improving traffic management and public transportation
by analyzing data from IoT sensors and devices.
★ Energy: Optimizing energy consumption and reducing waste by
analyzing data from smart meters and other IoT devices.
Industry and Manufacturing
★ Automobile Industry: Optimizing production processes and improving
vehicle design based on data analysis.
★ Food and Beverage Industry: Ensuring food safety and quality by
analyzing data from various stages of the production process.
★ Retail: Optimizing inventory management and supply chain operations
to reduce costs and improve customer satisfaction.
Other Domains
★ Retail: Improving customer satisfaction and increasing sales by
analyzing customer data and providing personalized
recommendations.
★ Telecommunications: Optimizing network performance and reducing
customer churn by analyzing usage data and customer feedback.
★ Education: Enhancing student learning outcomes by analyzing student
data and providing personalized educational content.
What is Business Intelligence?
★ Business Intelligence (BI) refers to the technologies, strategies, and
practices used to collect, analyze, and present business data.
★ It's a process of transforming raw data into actionable insights that drive
better decision-making.
★ Purpose: BI helps businesses understand their performance, identify
areas for improvement, spot market trends, and make informed strategic
choices.
★ Components: Data mining , Data Warehouse, Reporting Dashboards
Data visualization
Understanding Big Data's Role in BI
★ Data is the foundation: Business intelligence relies on data, and the
rise of big data has significantly expanded the scope and potential of
BI.
★ 3Vs: Big data, characterized by its massive volume, wide variety of
formats, and high velocity of generation, provides a much richer source
of information for BI.
★ Advanced analytics: BI leverages big data to perform more
sophisticated analyses, such as predictive modeling and sentiment
analysis, leading to deeper insights.
Benefits of Business Intelligence
Big Data Analytics vs. BI
Big Data Analytics vs. BI
Feature Big Data Analytics BI
Data Type Structured and unstructured data Primarily structured data

Data Volume Large volumes of data Smaller, more manageable

datasets

Analysis Focus Predictive and prescriptive analytics Descriptive analytics

Processing Speed Real-time or near real-time Batch processing, often

processing periodic

User Base Data scientists and analysts Business users and

decision-makers

In essence: BI uses historical data to understand the past and present, while
BDA explores large datasets to gain deeper insights and make predictions about
the future.
Future Trends
★ Edge Computing Integration
○ Processing data closer to the source to reduce latency.
○ Enhances real-time analytics for IoT and smart devices.
★ AI-Driven Big Data Analytics
○ Increased adoption of artificial intelligence and machine learning for deeper
insights.
○ Automated data analysis and decision-making processes.
★ Data Fabric Architecture
○ Seamless integration of diverse data sources and environments.
○ Enables unified data management across on-premises and cloud systems.
Future Trends
★ Quantum Computing Applications
○ Accelerating big data processing and complex problem-solving.
○ Potential to revolutionize industries like finance and healthcare.
★ Predictive and Prescriptive Analytics Expansion
○ Greater emphasis on forecasting and actionable recommendations.
○ Used in scenarios like supply chain optimization and personalized
healthcare.
★ Sustainability Analytics
○ Using big data to track and optimize energy consumption and carbon
footprints.
○ Supports green initiatives and environmental conservation.
Conclusion
★ Big Data Analytics is crucial for deriving insights from large datasets
★ Understanding the fundamentals, tools, and challenges is essential for
effective implementation
Quiz
1. Discuss the ethical implications of collecting and analyzing massive amounts of
personal data. How can organizations ensure responsible data practices?
2. How does Business Intelligence (BI) differ from Big Data Analytics in terms of
focus and purpose?
3. Explain the concept of the "5 Vs" of Big Data to a non-technical audience. Use
real-world examples to illustrate each V.
4. Explain the role of data mining in both Big Data and BI.
5. Describe a scenario where a company might need to use Big Data
technologies instead of traditional BI tools.