Customer Churn Prediction in the Telecom Sector

Customer churn, the phenomenon of customers terminating their subscription or services with a telecom provider, poses a significant challenge in the telecom industry. Predicting customer churn is crucial for companies to retain customers and minimize revenue loss. This paper presents a comprehensive approach to churn prediction using various machine learning(ML) and deep learning(DL) techniques, including Logistic Regression, Support Vector Machine (SVM), Random Forest, K Nearest Neighbours (KNN), Gradient Boosted Tree, and Multi-Layer Perceptron (MLP) Classifier. However, existing methods often suffer from limitations such as suboptimal accuracy and inability to capture complex patterns in the data. To address these drawbacks, this paper proposes a novel model called Hybrid Churn Prediction (HCP). The HCP model combines the strengths of different algorithms by integrating the predictions of multiple base models, resulting in improved accuracy and robustness in churn prediction. In this study, evaluation of performance of each individual model and comparison with the proposed HCP model is done using two distinct datasets from the telecom industry. The experimental results demonstrate that HCP model consistently outperforms existing methods, achieving higher accuracy in predicting customer churn.