Dapper Data
Perfect
Patterns
DSE NEWSLETTER Edition X
Table of Contents
Pearls
Words of Wisdom 01
The All Star
Employee Corner 02
The Go Getters
Placements 02
Timbre
Student Testimonials 07
Mindroids
Data Exploration 15
Model Building is an Art 15
Puzzle
Eight Puzzle Problem in AI
(Artificial Intelligence) 17
Industry Update 17
Editors of the Month 18
02
Pearls
Words of Wisdom
“It’s easy to lie with statistics It’s hard to tell
the truth without statistics.”
~ Andrejs Dunkels
“If you can’t explain it simply, you don’t understand
it well enough.”
~ Albert Einstein
03
Harshita
Assistant Manager - Career Preparation
Harshita Jhunjhunwala, a recent addition to the career prep team has donned many
feathers in her cap. From being a student in Digital Marketing to contributing in family
business for the past 6 years, mentoring students of primary schools, she has achieved
her dreams as a Mehndi designer. She calls herself a great multitasker, juggling between
her professional and personal life.
At GL, she has been able to support 40+ Placement processes and helped 20+ candidates
to achieve their goals and get final placements. She contributed to the creation of 45+
company courses which helped the candidates to prepare for company interviews.
People working with her always say that she is the real story of growth and learning, very
progressive in nature.
Her Slogan to work is “If you own it you achieve it”. Take the task or project as your own
and work wholeheartedly without thinking of success or unsuccess. Without trying no one
will be able to achieve success.
The Go Getters
Placements
"They Can" because they can do anything. "They Do it" because they believe in it. "They
Didn't Wait" because they trusted Great Learning as their career game-changer.
Those who made a career transition in the data science domain without having any prior
knowledge or background, it's because of sheer passion & we take this Hall of Fame as the
platform to salute you because it's "You" who could, it's "You" who did, it's "You" who made
it to the other side by taking that extra mile! Congratulations, we are proud of "YOU"!
A few of our hiring partners from last month:
Reliance Industries Limited EXL Indegene Private Limited Accenture
Daicto Technologies Capgemini Great Place to Work Tiger Analytics
Tech Mahindra Ecolab CGI NielsenIQ
04
Below are just a few of many transitions
from our recent placements.
Career Transition of Freshers:
Location: Pune
Full Name: Mandar Pimparkar
Education Background: BE Computer Science
Previous Designation: Fresher
Previous Company: NA
New Company: Capgemini
Location: Pune
Full Name: Sanket Bhavar
Education Background: BE Computer Science
Previous Designation: Fresher
Previous Company: NA
New Designation: Associate Data Scientist
New Company: Ecolab
Location: Mumbai
Full Name: Janhavi Sunil Gujar
Education Background: BE Computer Science
Previous Designation: Fresher
Previous Company: NA
New Designation: Project Engineer Trainee
New Company: Reliance Industries Limited
Location: Bangalore
Full Name: Aradhana Coelho
Education Background: BE Mechanical Engineering
Previous Designation: Fresher
Previous Company: NA
New Designation: Business Analyst
New Company: Great Learning
05
Career Transition of Experienced:
Location: Pune
Full Name: Karthik Shetty
Education Background: BE Mechanical
Previous Designation: Data Analyst
Previous Company: Urban company
New Designation: Data analyst trainee
New Company: Diacto Technologies
Location: Mumbai
Full Name: Suhas Namdeo Pawar
Education Background: BE Mechanical
Previous Designation: Quality Analyst
Previous Company: Karbon steel Mart Pvt Ltd
New Company: Jr Analyst
New Company: Tech Mahindra
Location: Hyderabad
Full Name: Shaik Lal Zaheer Hussain
Education Background: BTech Computer Science
Previous Designation: Software Dev Engineer
Previous Company: Erwin-Quest
New Designation: Software Engineer
New Company: CGI
Location: Bangalore
Full Name: Lucky Agarwal
Education Background: BE Production Engineering
Previous Designation: Faculty
Previous Company: Prospexive Eduvision Private Limited
New Designation: Senior Analyst
New Company: EXL
06
Timbre
Student Testimonials
Student Testimonials from
the Fresher candidates:
Location: Chennai
Full Name: Ramya Devi R
Education Background: BTech Leather Technology
Previous Designation: NA
Previous Company: NA
New Designation: Data Scientist
New Company: Indegene Private Limited
I joined the DSE course in GL with zero coding Knowledge. This course is very beginner friendly,
especially Introduction to Python course mentors taught us from scratch. It helped me a lot to
get the basic knowledge about coding. The lab sessions were worth the time and helped me to
do lots of hands on with the gaudiness of the mentors. I would like to thank Meena mam,
whenever I had a doubt in the sessions she took her time and made sure that the concepts were
clear. The SQL Modules taught by Deepali mam helped me to get a quick grasp on the concepts.
I would Like to thank Sachin sir for Statistics and Anand Babu sir for Machine Learning for the
way they taught the concepts with real time examples, it was easy to understand the concepts
which were very new and different to me. Initially the course was pretty much difficult for me but
soon with the help of the mentor’s learning session, in class and take-home activities, learning
content provided for each of the modules has helped me to understand the concepts very well.
This DSE course helped me a lot to get a good understanding of all the basic concepts of Data
Science to be future ready.
Location: Pune
Full Name: Sanket Bhavar
Education Background: BE Mechanical
Previous Designation: NA
Previous Company: NA
New Designation: Associate Data Scientist
New Company: Ecolab digital Center
Hello everyone! My name is Sanket Bhavar. I am a Mechanical engineering pass out and it gives
me great pleasure that I have completed my PGP in Data science and Engineering from Great
Lakes institute. I always wanted to be in the field Data science program. Great Learning has
provided me with the perfect platform to build on my career with access to well-designed
07
curriculum, faculty and supporting management. At first, I was having doubts about my coding
skills because of my mechanical background but their team is pragmatic and the course content
comprehensive, with highly qualified mentors who possess rich experience in the relevant field.
Because of that I felt the whole course was very easy. Thus, altogether an awesome experience.
The faculty helps you at every point and the best part is the evaluation method. After completing
each module we need to give quizzes and tests which helps a lot to prepare. Also, the curriculum
is too good. We get study materials, recorded video lectures, flip videos, peer guru sessions and
much more!! The relationship between faculties and students is very cordial, which gave me the
opportunity to excel in my career. The one year spent here was very splendid and has helped me
a lot to grow professionally as well as personally.
Thanks to Great Learning for Helping me to successfully transition in the Data Science Industry.
Wishing Great Learning Many Success Stories ahead!
Location: Bangalore
Full Name: Venkata Rajesh G
Education Background: BCA
Previous Designation: NA
Previous Company: NA
New Designation: Data Scientist
New Company: Great Learning
A truly Great Institute is Great Learning
I got one of the best faculties and mentors when I was studying Data Science at Great Leaning.
Great Learning provided me with enough hands-on experience, I feel glad that I met different
kinds of good people and friends on this journey. Coming to placement service, I have never seen
any placement service like GL provides. Great Learning gave me a diverse set of notes for
different companies that made me clear my first two companies. I wanted to show my gratitude
to Great Learning in the past of this journey and I am lucky enough that I got placed in Great
Learning itself. Words are not adequate to describe my gratitude for GL.
Location: Online
Full Name: Faizan Khan
Education Background: BTech Mechanical
Previous Designation: NA
Previous Company: NA
New Designation: Senior Analyst
New Company: Capgemini
08
“Great Learning is a place that makes our dreams come true. Great Learning transforms a person
from low coding and analytical skills to a person with good coding and analytical skills with
well-experienced staff members having in-depth knowledge. I have experienced enriched
placement assistance in Data Science and Engineering courses for getting placement. Thank you,
Great Learning for your kind and tireless support.”
Location: Online
Full Name: Smruthi Bhandiwad
Education Background: BE Mechatronics
Previous Designation: NA
Previous Company: NA
New Designation: Associate
New Company: Accenture
Data Science and Machine Learning: Making Data-Driven Decisions” provided by “Great
Learning” and “MIT-IDSS” is a journey in itself. Just before the lockdown my father suggested me
about the Data Science course when I was in my final year of mechatronics. In the beginning I
found that the data science was completely different from my field but later when I started
learning from the Great learning platform, I got a hold on how I can connect data science with
my field. So, I opted for a Post Graduation Data Science course which is for a 9-month duration.
The program material, level of quizzes, project work all was designed considering one’s learning
speed, workload, and capacity to achieve. The best part about it was that they taught us from
scratch. I had no idea about python before I opted for the course. We learners also got a chance
to connect with other enthusiastic people across the globe during the mentor sessions of the
program. It was indeed a great practice knowing how people are evolving themselves in the
world of data science. I would like to thank all the mentors for giving and teaching us an
abundance of knowledge. I would like to thank Varsha P mam, who guided me to the end of the
course and boosted up my confidence. If you are looking for magic to happen in your thinking
towards data science and ML, then this course is best to accomplish! Please go ahead and enrol
yourself without any doubt.
09
Career Transition of Experienced:
Location: Online
Full Name: Krishnat Mane
Education Background: BE Mechanical
Previous Designation: BE Mechanical
Previous Company: Glasstech Industries India Pvt. Ltd.
New Designation: Data analyst
New Company: NielsenIQ
This is Krishnat Mane. Before entering into the program, I was a professional Production Engineer
in core mechanical field and I didn’t even know the name of languages that I learned during the
program. But after losing my job in the Corona pandemic I decided to do a Postgraduate
program in Data Science with great learning. I feel very happy to say that my entire journey with
great learning was too good because of their teaching staff, their management and their support
in the placement process. I learned things very fast thanks to the teachers and the way they
taught was so good. I would like to express my gratitude to the faculty, mentors, career prep
team and GL management for their guidance and support throughout the journey.
Location: Bangalore
Full Name: Anandu PN
Education Background: BTech Mechanical
Previous Designation: Designer - Piping
Previous Company: Bilfinger Tebodin India Pvt. Ltd.
New Designation: Analyst - Data Science
New Company: Tiger Analytics
I am extremely happy to share my journey with Great Learning. As a student from non-IT
background, it’s hard for me in the starting phase. But through the proper mentoring and
guidance from Great Learning and faculties, I was able to catch up all and make myself confident
about the tools and skills. I would like to thank you Aniruddha sir, Rakesh sir, Varsha mam,
Gulshan, Angel, Sagarika, Mahesh Anand, Cyan sir and each and every faculty member who
helped me to start my career in the field of data science. Initially I got an offer from Tesco
through GL, but at the same time I got another offer from Tiger Analytics which I applied
through off campus. Finally with the guidance of varsha mam I choose Tiger Analytics.
Once again Thanking GL for the smooth journey
10
Location: Mumbai
Full Name: Kimaya Vilas Manjrekar
Education Background: BE IT
Previous Designation: Associate Consultant
Previous Company: Atos Syntel Pvt Ltd
New Designation: Research Analyst
New Company: Great Place to Work
While thinking about Data Science, think about Great Learning. When I decided to have a career
transition from being an iOS Developer into Data Science, Great Learning seemed an appropriate
choice for the same. The curriculum is based on industry relevant modules in order to allow
learners to gain knowledge from base and from industry led experts who are very focused to
impart knowledge and help learners to be a step ahead. The placement team has been extremely
supportive and alert in monitoring the progress of learners during placement also providing
technical mentors who help us to better our performance during interviews.
Location: Bangalore
Full Name: Lucky Agarwal
Education Background: BE Production Engineering
Previous Designation: Faculty
Previous Company: Prospexive Eduvision Private Limited
New Designation: Senior Analyst
New Company: EXL
The best decision I opted for Career transition in the field of analytics was by opting for the
program at Great Learning. The course is really well structured, daily in class, quizzes, case study
sessions and home assignment helped a lot to make this journey of learning smooth. The in
-depth concept clarity and extensive support provided by the placement team helped me to
crack my interview easily. Would like to thank all the Great Learning team for this beautiful
learning experience.
Location: Online
Full Name: Akash Sah
Education Background: BE EEE
Previous Designation: Senior System Engineer
Previous Company: EY India
New Designation: Associate Consultant
New Company: EXL
11
Hi,
Let me share my journey and how I came up with my decision on this course.
At the time when I joined Great Learning I had completed my 2 years of experience in Infosys. I
was working in ‘Oracle’ database which introduced me to the world of data and also motivated
me towards it. After that I have searched for multiple sources from where I can learn data
science more deeply. So I started Learning data science from YouTube mainly from Krish Naik
videos which was very helpful and I have done multiple kaggle projects and also I have done this
online Great Learning course which helped me to have peer to peer learning and also made my
study consistent. Once I completed my learning part I had updated my resume on Naukri profile
from which I got multiple offers before completing my Great Learning course itself like:
TCS, Tiger Analytics, KPMG, Cognizant, Blue Yonder, Bridgei2i, Accenture, McKinsey & Company.
Also got placed from Great Learning Placement in EY.
Great Learning is a good course to get an introduction to data science for the person new in IT
or wants to transition into IT.
12
Mindroids
Data Exploration
Nivedhan SenthilKumar
PGP DSE – Chennai Jan 21
Hang on you read it right, yes, it is so much an art as much as it is science! Every artist has his
own way of building his art and even every data scientist has different approaches to the same
business problem in a different way. And that’s what makes this such a dynamic field. When we
come to a saturation on a dataset thinking this is the best result possible BOOM, you see
someone on the Kaggle leader board with a better solution we go DAMN!!!! So if that’s the case
what makes a good Data Scientist, the short answer is EVERYTHING!! Good knowledge of math,
creativity, DOMAIN KNOWLEDGE, etc. So we will go by addressing every single component
specifically.
GOOD MATH:
Good is a very subjective term I feel, so let me coin adequate so what is adequate knowledge of
math needed? The short answer is IT DEPENDS
Say you work on a regression problem to predict the marks of a student then the knowledge of
linear algebra become critical. In scenario 2 you are trying to predict whether a patient will get
diabetes or not then there it is a question of probability.
So the amount of math ranges from simple variance to complex differential equations.
13
DOMAIN KNOWLEDGE:
This is the hardest puzzle to crack in the ML Spectrum. Every industry is different and its
challenges are different. So how to go about choosing a domain? To take a domain of interest
it should be relatable in the first place. Say you love sports “SPORTS ANALYTICS” can be a
good choice. So a good starting point would be to download a Kaggle dataset and then work
on it.
If you hold an MBA in Marketing and are trying to venture into Data Science, then MARKETING
ANALYTICS would be the way to go.
Try finding what interests you in general and explore the data science opportunities in it.
CREATIVITY:
This is a tough puzzle to crack. The ability to have a lot of tricks under sleeves also makes life
easier. When you know a lot of methods you automatically become creative by trying to
combine multiple models and trying to solve it at efficiency.
Along with efficiency, the brute force of being able to dig the best methods by lots of
experiments and the ability to be persistent is a much needed skill in the data spectrum.
So trying to be open while solving a business problem is the most important thing to have.
There are different approaches to Model Building but I have listed
down the approach I use which has worked for me in most occasions
STEP 1 : Perform Exploratory Data Analysis (EDA)
STEP 2 : Perform Feature Engineering
STEP 3 : Perform Statistical tests to identify statistical significance
STEP 4 : Build a baseline model
STEP 5 : Build a simple model (Linear or Logistic Regression)
STEP 6 : Interpret the coefficients and other statistical measures from the statmodels.
STEP 7 : Build the basemodel for all models with default parameters using AUTOML.
STEP 8 : Identify the best performing models (minimum 4)
STEP 9 : Using Feature Selection Techniques select the best features
STEP 10 : First build the model using all the features (This is sort of benchmark)
STEP 11 : Now build the model using the selected features
STEP 12 : Tune the model for hyperparamters for better performance.
STEP 13 : Identify the best single model with hyperparamters and measure performance.
STEP 14 : Ensemble models (combination of multiple models) and measure their performance
14
STEP 15 : In ensemble models there are certain definite combinations to try out – Bagging
combinations, Boosting combinations, Bagging + Boosting Combinations, Tree model
combinations,
Regularization model combinations, Linear model combinations.
STEP 16 : Identify the best model among all the experiments
STEP 17 : Log the important features to have a clear idea of what features contribute high to the
predictions
STEP 18 : Ship the model in a production ready manner ready to be deployed.
The steps can be changed depending on the business problem and the type of data at hand.
While important to be flexible most parts of this step would be a part of any machine learning
problem.
Puzzle
Eight Puzzle Problem in AI
(Artificial Intelligence)
Problem:
We also know the eight puzzle problem by the name of N puzzle problem or sliding puzzle
problem.
N-puzzle that consists of N tiles (N+1 titles with an empty tile) where N can be 8, 15, 24 and so on.
In our example N = 8. (that is square root of (8+1) = 3 rows and 3 columns).
In the same way, if we have N = 15, 24 in this way, then they have rows and columns as follows
(square root of (N+1) rows and square root of (N+1) columns).
That is if N=15 then number of rows and columns= 4, and if N= 24 number of rows and columns=
5.
So, basically in these types of problems we have given an initial state or initial configuration
(Start state) and a Goal state or Goal Configuration.
Here We are solving a problem of 8 puzzles that is a 3x3 matrix.
Initial state Goal state
1 2 3 1 2 3
4 6 4 5 6
7 5 8 7 8
*Solution available at the end of the newsletter.
Game credits: Venkatarajesh G (GL Data Scientist, Acad Ops)
Source: www.goeduhub.com
15
Industry update
"As per Stanford’s AI Index Report , India (2.83 times the global average) has the highest relative
AI skill penetration rate (based on the data from 2015-20), followed by the US, China and
Germany."
Editor-in-chief
Jennifer Carlisle
Great Learning, DSE Operations
Editors of the Month
Devyani Acharya Venkatarajesh G
Senior Career Preparation Manager Data Scientist
16
Solution to the Game
The puzzle can be solved by moving the tiles one by one in the single empty space and thus
achieving the Goal state.
Rules of solving puzzle
Instead of moving the tiles in the empty space we can visualize moving the empty space in place
of the tile.
The empty space can only move in four directions (Movement of empty space)
Up
Down
Right or
Left
The empty space cannot move diagonally and can take only one step at a time.
All possible move of a Empty tile
O X O
# X
O X O
O - Position total possible moves are (2), x - position total possible moves are (3) and
# - position total possible moves are (4)
Let's solve the problem without Heuristic Search that is Uninformed Search or Blind Search (
Breadth First Search and Depth First Search)
Breath First Search to solve Eight puzzle problem
17
Start Node
1 2 3
4 6
7 5 8
Right Move Up Move Down Move
1 2 3 1 2 3 1 2 3
4 6 4 6 7 4 6
7 5 8 7 5 8 5 8
Explore all possible move for each node (i.e.U,D,R,L)
Down Move Left Move Right Move Up Move
1 2 3 1 2 3 1 2 3 1 3
4 5 6 4 6 4 6 4 2 6
7 8 7 5 8 7 5 8 7 5 8
Explore all possible move for each node
1 2 3 1 2 3
4 5 6 4 5 6
7 8 7 8
Goal Move
Note: If we solve this problem with depth first search, then it will go to depth instead of exploring
layer wise nodes.
Time complexity: In worst case time complexity in BFS is O(b^d) know as order of b raise to
power d. In this particular case it is (3^20).
b-branch factor
d-depth factor
Let's solve the problem with Heuristic Search that is Informed Search (A* , Best First Search
(Greedy Search))
To solve the problem with Heuristic search or informed search we have to calculate Heuristic
values of each node to calculate cost function. (f=g+h)
18
Initial state Goal state
1 2 3 1 2 3
4 6 4 5 6
7 5 8 7 8
Note: See the initial state and goal state carefully all values except (4,5 and 8) are at their
respective places. so, the heuristic value for the first node is 3.(Three values are misplaced to
reach the goal). And let's take the actual cost (g) according to depth.
Start Node
g=0, h=3, f=g+h=3
1 2 3
4 6
7 5 8
g=1, h=4, f=5 g=1, h=2, f=3 g=1, h=4, f=5
2 3 1 2 3 1 2 3
1 4 6 4 6 7 4 6
7 5 8 7 5 8 5 8
g=2, h=1, f=5 g=2, h=3, f=5 g=2, h=3, f=5
1 2 3 1 2 3 1 3
4 5 6 4 6 4 2 6
7 8 7 5 8 7 5 8
g=3, h=2, f=5 g=3, h=6, f=3
1 2 3 1 2 3
4 5 6 4 5 6 Goal Node
7 8 7 8
Note: Because of quick solution time complexity is less than that of Uninformed search but
optimal solution is not possible.
19
ADMISSION ENQUIRY - 080 4717 7774
THANK YOU
20
