Minimization of Churn Rate Through Analysis of Machine Learning

Attrition of customers is another name for customer churn. Today, there are an increasing number of clients who leave each year - nearly 1.5 million on average. The banking sector confronts difficulties keeping customers. Due to shifting factors, such as better financial services at cheaper costs, bank branch location, low interest rates, etc., customers may decide to switch banks. As a result, prediction models are used to identify clients who are likely to leave in the future. Because maintaining long-term relationships with consumers is less expensive than losing a customer, which causes a loss of profit for the bank. Older consumers also generate greater rewards and offer fresh references. 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 used and also the comparison in terms of performance like accuracy, recall, etc. is presented. Among these classifiers Random Forest has achieved best accuracy of 71%.