1 of 9

REVA HACK- 2021�Patron Augury

Team name: STARK

Team Leader: Sowmya Sree T

Team members: C Sri Sravya

                              Raksha R Y

Theme:

Customer churn prediction

2 of 9

Problem Statement

  • Companies are working hard to survive in today’s competitive market as a result, increasing the cost of customer acquisition
  • It is therefore essential for the service providers to prevent churn
  • Churners are persons who move to other bank for various reasons
  • The aim of Customer Churn Prediction Model is to detect customers with high tendency to leave a bank

​

​

3 of 9

Necessity of the model

  • Provide exceptional Customer service 
  • Helps manage the direct loss of revenue
  • Reduce the risk of business
  • Detailed and graphical form of information helps improvement of service

​

4 of 9

Sources used

Random Forest Algorithm through Machine Learning

Kaggle Data Set

Comprises 10000 customers

Spread over 10 attributes

Python Libraries

Numpy

Pandas 

MatPlotLib

Seaborn

Scikit learn

​

​

5 of 9

Proposed Solution

  •  We try to build a model that uses Random Forest Classification to identify the churn customers 

​

  • It also provides the factors behind the churning of customers in the banking sector

​

​

6 of 9

Attributes used for analysis

Credit score 

Location of the Customer 

Gender 

Age

Tenure 

Account Balance

Number of Bank Products Customer Uses 

Has Credit Card 

Is Active Member 

Estimated Salary

7 of 9

8 of 9

Conclusion

  • In future , the model can be further extended to explore the changing behavior patterns of churn customers by applying AI

​

  • We can also make an option for other banks to add data and various other attributes to this dataset for their churn analysis 

9 of 9

THANK YOU