Customer Churn Prediction in Telecommunication Industry Using Classification and Regression Trees and Artificial Neural Network Algorithms

Customer churn is a serious problem, which critical issue encountered by large businesses and organizations. Due to the direct impact on company's revenues, particularly in sectors such as telecommunications well banking, companies are working promote ways identify of prospective consumers. Hence it vital investigate issues that influence customer yield appropriate measures diminish churn. The major objective this work advance model prediction helps telecom operatives envisage clients most probable be subjected experimental approach for study uses machine learning procedures dataset, using an improved Relief-F feature selection algorithm pick related features from huge dataset. To quantify model's performance, result classification CART ANN, accuracy shows ANN has high predictive capacity 93.88% compared 91.60% classifier