Request Feature

• About the Project
  • Built With
• Usage
• Roadmap
• Contributing
• License
• Contact
• Acknowledgements

A churn model is a mathematical representation of how churn impacts your business. Churn calculations are built on existing data (the number of customers who left your service during a given time period). A predictive churn model extrapolates on this data to show future potential churn rates.

Churn (aka customer attrition) is a scourge on subscription businesses. When your revenue is based on recurring monthly or annual contracts, every customer who leaves puts a dent in your cash flow. High retention rates are vital for your survival. So what if we told you there was a way to predict, at least to some degree, how and when your customers will cancel?

That’s exactly what a churn model can do.

Building a predictive churn model helps you make proactive changes to your retention efforts that drive down churn rates. Understanding how churn impacts your current revenue goals and making predictions about how to manage those issues in the future also helps you stem the flow of churned customers. If you don’t take action against your churn now, any company growth you experience simply won’t be sustainable.

Comprehensive customer profiles help you see what types of customers are canceling their accounts. Now it’s time to figure out how and why they’re churning. Ask yourself the following questions to learn more about the pain points in your product and customer experience that lead to a customer deciding to churn.

There’s no more vital metric for a SaaS company to keep track of than churn: the rate at which customers are leaving your business and taking their subscription dollars elsewhere. Churn can be powered by a number of factors, and even small month-on-month increases in churn percentage can be ruinous to planning, so understanding what churn is and how to analyze it is paramount.

This was build using following frameworks, libraries and softwares.

• Numpy
• Scikit-learn
• Keras
• Matplotlib
• Pandas

Churn analysis is useful to any business with many customers, or to businesses with few, high-value customers. Which is to say, nearly every company. Companies in different industries use customer churn analytics for a variety of reasons:

• Financial services: Measure account holder lifecycle, detect users thinking of switching banks
• Consumer packaged goods: Develop a support model that encourages loyalty
• Consumer tech: Measure app churn
• Energy: Measure how much revenue is at risk of being lost to other providers
• Healthcare: Calculate the value of patients lost to other providers
• Insurance: Predict a user’s likelihood to close a policy
• Life sciences: Measure churn for device or equipment buyers
• Manufacturing: Measure churn for direct and downstream buyers
• Media and entertainment: Measure subscriber churn
• Retail and e-commerce: Predict when shoppers pose a high churn risk
• Telecommunications: Detect when customers are shopping other carriers
• Travel: Measure churn among repeat web visitors

For more examples, please refer to the Article

See the open issues for a list of proposed features (and known issues).

Contributions are what make the open source community such an amazing place to be learn, inspire, and create. Any contributions you make are greatly appreciated.

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

• MIT license
• Copyright 2020 © Aditya Mangla.

Aditya Mangla - @aadimangla - [email protected] - adityamangla.com

Project Link: https://github.com/aadimangla/Churn-Modelling-for-a-Bank

• SuperDataScience