Enhancing Customer Retention: CNN-Based Churn Prediction in Telecom

Abstract

In this competitive world, business is becoming highly saturated. Especially, the field of telecommunication faces complex challenges due to a number of vibrant competitive service providers. Churn Examination is one of the widespread used study on analysing the behaviour and activities of customers in order to predict beforehand which customer is likely to exit the service agreement. Churn prediction is very essential in telecom industries to retain their customers. According to an article in Harvard Business Review (Gallo, 2014), it was determined that the cost of acquiring a customer is five to twenty-five times more than retaining an existing one. Furthermore, by increasing retention by five percent can lead to an increase in profits by twenty-five to ninety-five percent. This paper applies classification and deep learning algorithms to predict the behaviour of customer retention on a telecom dataset extracted from Kaggle. Additionally, this paper also aims to build a churn prediction model and use that model to identify customers likely to churn. In order to measure the performance of the model, the Area Under Curve (AUC) standard measure is adopted.