Machine Learning-Based Customer Churn Prediction System for Banking Applications with Explainable AI

The Bank Customer Churn Prediction System is an end-to-end machine learning application designed to predict whether a customer is likely to leave a banking service. The system utilizes customer attributes such as credit score, age, balance, tenure, and activity status to generate accurate churn predictions. An interactive web interface is developed using Streamlit, allowing users to input customer details and receive real-time predictions along with probability scores. The application also includes a visual analytics dashboard that presents key insights, trends, and factors influencing customer churn. Furthermore, the system incorporates batch processing for handling multiple customer records, explainable AI techniques using SHAP for model interpretability, and sensitivity analysis to understand the impact of individual features on predictions. By integrating machine learning with business intelligence, the proposed system provides a practical and data-driven solution to improve customer retention strategies and enhance overall service quality.