1. MAHARAJA INSTITUTE OF TECHNOLOGY
THANADAVAPURA
“INTERNSHIP FINAL PROJECT”
-Prerana T S
4MN20IS021
7th SEM
Information Science and Engineering
Under the guidance of :
Prof. Mohammed Salamath
Asst.professor
Department of ISE
2. • Institute Introduction
• Topics coverd in week 1
• Topics coverd in week 2
• Topics coverd in week 3
• Topics coverd in week 4
3. • The Institution of Electronics and Telecommunication
Engineers(IETE) is India's leading recognized professional
society devoted to the advancement of Science and Technology
of Electronics Telecommunication & IT,founded in 1953.
• The IETE is the National Apex Professional body of Electronics
and Telecommunication, Computer Science and IT
Professionals. It serves more than 1,25,000 members (including
Corporate, Student and ISF members) through various 64
Centres, spread all over India and abroad.
• IETE Mysore centre aims at imparting knowledge to the
students and the teaching fraternity of polytechnic and
engineering colleges through workshops and FDPs on latest
technology in association with both academia and industry.
Contact :
Phone no : 9738686704
e-mail ID :
mysuruietecenter@gmail.com
4. : (14-08-23 to 19-08-23)
• Overview of Data Science : Data science encompasses
various disciplines such as statistics, machine learning, data
analysis, data visualization, and domain expertise.
• Introduction to python : Python is a versatile and powerful
programming language for data science that offers a wide
range of libraries and tools.
5. WEEK 2 : (21-08-23 to 26-08-23)
Python for Data Science :
• "Python for Data Science" refers to the use of the Python
programming language and its associated libraries and tools
for tasks related to data analysis, data manipulation, data
visualization, and machine learning.
6. WEEK 3 : (28-08-23 to 02-09-23)
Understanding stastistics for Data Science :
• Understanding statistics is a fundamental aspect of data
science.
• Descriptive Statistics: These methods help summarize and
describe data.
• Inferential Statistics: Inferential statistics are used to make
predictions, draw inferences, and test hypothesis .
7. WEEK 4 : (04-09-23 to 09-09-23)
Prediction modeling and basics of Machine Learning :
• Prediction modeling and the basics of machine learning are
core components of data science.
Real time application assessment and Mini Project :
• The project I worked on is “ Telecom Churn Prediction ”.
9. • Introduction
• Project Objective
• Dataset Descriptive
• Churn Prediction Model
• Methodologies
• Exploratory Data Analysis
• Bar Graph
• Box Plot
• Scatter Plot
• Accuracy Of Various Models
• SVM Model
• Metrics Evalution
• Findings And Suggestions
• How To Reduce Customer Churn
• Conclusion
10. INTRODUCTION
• Churn prediction is one of the most popular Big
Data use cases in business. It consists of detecting
customers who are likely to cancel a subscription
to a service.
• Churn is a problem for telecom companies
because it is more expensive to acquire a new
customer than to keep your existing one from
leaving.
11. • To predict Customer Churn.
• Highlighting the main variables/factors
influencing Customer Churn.
• Use variables ML algorithms to build
prediction models, evaluate the accuracy and
performance of these models.
• Finding out the best model for our business
case & providing executive summary.
PROJECT OBJECTIVE
12. DATASET DESCRIPTION
• Source dataset is in CSV format.
• Dataset contains 7043 rows and 14 columns
• There is no missing values for the provided
input dataset.
• Churn is the variable whether a particular
customer is churned or not.
14. METHODOLOGIES
• EDA(Exploratory Data Analysis): The dataset
consists of 12 variables in all. A few are
continuous, and rest are categorical. The control
variables are customers.
• Model building which includes defining the
purpose if model, determine the model boundary,
build the model, create an interference and export
the model.
• Evaluating machine learning algorithm is an
essential part of project.
15. EXPLORATORY DATA
ANALYSIS
• Data visualizing using seaborn and matplotlib
• EDA(Exploratory Data Analysis) is an approach
to analysis data sets and to summarize their
main characteristics, aften with visual methods.
• A statistical model can be used or not, but
primarily EDA is for seeing what the data can
tell us beyond the formal modelling or
hypothesis.
16. BAR GRAPH
• Plot shows that the users from the
data are likely to be continuing their
subscription plan(>70%)
Fig 1.1 : Bar Chart
17. BOX PLOT
• We found outliers in exiting customers which is out
of whiskers.an outlier is an observation that is
numerically distant from the rest of the data.
• Using skew()method we found that churn data is
inconsistent with tenure
• Customers who disconnecting their subscription
plans are selecting short tenure telecom company
need to offer better plans for those customers who
choose short tenures
Fig 1.2 : Box-and-Whisker Plot
18. SCATTER PLOT
• Customers paying high monthly charges
for short tenures are disconnecting
• Customers paying high monthly charges
for long tenures continuing with their
subscription plans, as it is reasonable cost
Presentation title
Fig 1.3 : Scatter Chart
23. FINDINGS AND SUGGESTIONS
• Try to offer the better service for the churn customers, see how
much this impact before and later. some may use your service
better move them to your active customers.
• Take the feedback and suggestions with in period of time and
improve it strive for better communication.
• When you are taking the any change in plans of your business
just predict the positive and negative share of that plan. if it is
negative prepare the solution before so you can handle easily.
24. HOW TO REDUCE CUSTOMER
CHURN
• Learn into your best customers.
• Be proactive with communication.
• Define a roadmap for your new customers.
• Offer incentives.
• Ask for feedback often.
• Analyze churn when it happens.
• Stay competitive.
25. CONCLUSION
• The important of this type of research in the telecom market is to
help companies make more profit.
• It has become known that predicting churn is one of the most
important sources of income to telecom companies.
• Hence, this research aimed to build a system that predicts the
churn of customers telecom company.
• These prediction model need to achieve high AUC values.to test
and train the model, the sample data is divided into 70%for
training and 30%for testing.
