Customer Churn Analysis and Prediction in Banking Industry using Machine Learning

Abstract

Customer Churning is also known as customer attrition. Nowadays, there are almost 1.5 million customers that are churning in a year that is rising every year. The Banking industry faces challenges to hold clients. The clients may shift over to different banks due to fluctuating reasons, for example, better financial services at lower charges, bank branch location, low-interest rates, etc. Thus, prediction models are utilized to predict clients who are probably going to churn in the future. Because serving long-term customers is less costly as compared to losing a client that leads to a loss in profit for the bank. Also, old customers create higher benefits and provide new referrals. In this paper, different models of machine learning such as Logistic regression (LR), decision tree (DT), K-nearest neighbor (KNN), random forest (RF), etc. are applied to the bank dataset to predict the probability of customer who is going to churn. The comparison in terms of performance like accuracy, recall, etc. is presented.