Customer Churn Prediction in Banking

According to estimates, it is five times more costly to attract new customers than retain existing ones. Preventing customer churn has thus become an essential issue in many sectors, including banking. Using churn prediction models, banks can identify potential leavers and then decide on the right course of action to prevent their departure.

Our client - the Polish branch of an international banking institution - also reached for such models, but was looking for ways to improve the existing system.


Industry: FinTech, Banking, Customer Experience

Project Category: AI, data analytics, software development

Lead Member: QuantUp




Project Description & Client Benefits


Together with the client, our team performed a deep refactoring of the client's churn prediction model. We dealt with both the business and technical aspects of the existing solution, extending the scope of the analyzed datasets with unstructured text data describing transactions made by customers. In the modeling process, we implemented Machine Learning techniques. At the end of the project, we also organized a workshop dedicated to our client's team to help him build the competences needed to fully use the new solution and create similar models without our help.


The new model significantly improved our client's customer churn forecasts - by more than 10% compared to the previous model. As a result, our client has optimized related processes and is now better able to identify customers at risk of churn and prevent churn.

23 views