CUSTOMER CHURN PREDICTION IN TELECOM INDUSTRY

Abstract

Customer churn is a critical challenge in the telecom industry, where retaining existing customers is often more cost-effective than acquiring new ones. This project focuses on predicting customer churn using machine learning techniques and visualizing the results through a web-based application. The study employs Jupyter Notebook for comprehensive data processing, visualization, and the implementation of machine learning models including Random Forest, Logistic Regression, and Multi-layer Perceptron (MLP). Among these, the Random Forest algorithm demonstrated the highest performance with an accuracy of 99%, outperforming Logistic Regression (98%) and MLP (97%). The project also includes the development of a Django-based web interface for category-wise churn visualization and real-time prediction based on user-uploaded test data. Users can interactively explore churn patterns by various filters such as gender, service type, and geography, enhancing interpretability and business decision-making. This integrated approach provides a powerful tool for telecom companies to proactively manage customer retention strategies.