Smart Customer Churn Management System Using Machine Learning

Abstract

While the speed of digitalization is rapidly evolving, the importance of the competition and customer experience is simultaneously gaining prominence. It is crucial for banks to understand the needs of customers and offer special products or opportunities accordingly, through developing automated systems that monitor and analyse reasons for customer churn and predict customers who are likely to leave in the future. The system aims to improve customer satisfaction by reducing customer churn, which is a term used to describe the loss of clients or subscribers for whatever reason from an organisation. This research seeks to leverage on the core processes of machine learning involved in building such a system, in order to address the business question ‘How to prevent customer attrition or churn?’ The adopted methodology involves four different phases, namely, data preparation and processing, feature extraction, dataset and testing, performance evaluation. Six classification algorithms are applied and compared against each other, and the best performing model is selected for the system implementation. In comparing the models, random forest classifier is selected with the accuracy of 87% and precision of 85%.