Skip to content

apollo-robin/customer-churn

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

88 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Predict Customer Churn

One of the problems any company faces is the churn of customers. This project aims to solve this problem by predicting churn of credit card customers and help banks to act proactively to retain these customers by providing them better services.
Live demo here.

Table of Contents

General Information

  • This project intends to solve the problem of cusotmer churn by prediciting customers who are likely churn.
  • Predicitions are made using Machine Learning techniques for Classification.
  • The model is trained on data from 10k credit card users with 18 features.
  • This project is part of a course on Machine Learning Operations.

Technologies Used

  • Python 3.7

Features

  • Predict which of your customer may churn
  • Know the reasons for churn with Global and Local Model Explainability
  • Data Drift Report and Model Scorecard

Screenshots

Example screenshot

Setup

The requirements are specified in the requirement.txt file in Python Files directory.

Usage

The easier way to use the model is to go to the Web Interface. Secondly all the Notebooks can be opened directly in Google Colaboratory.

Project Status

Project is: in progress

Acknowledgements