Customer Churn Prediction for Telecommunication Operator

Abstract

Client turnover is a significant issue and one of the most pressing issues for large businesses. Companies are working to develop methods to predict potential customer churn because it has such a direct impact on their revenues, especially in the telecom industry. As a result, identifying factors that contribute to consumer churn is critical in order to take the appropriate steps to minimize churn. Our work's key contribution is the creation of a Churn Prediction model that helps Telecom operators predict which customers are more likely to churn. The model created in this paper employs machine learning techniques on a big data framework to create a novel approach to feature engineering and selection. The Area under ROC Curve standard measure is used to assess the model's efficiency, and the ROC curve value obtained is 98 percent.