A Comparative Study of Machine Learning Algorithms for Bank Customer Churn Prediction

A Comparative Study of Machine Learning Algorithms for Bank Customer Churn Prediction

 Prashant Kumar Himanshu

 UG Students, Department of Electronics & Communication Engineering, Acharya Institute of Technology, Bangalore

prashantr.19.ait@gmail.com

Abstract— Bank churn, or the phenomenon of customers leaving their bank for another, is a major concern for financial institutions. The ability to predict churn can help banks to retain customers, reduce costs, and increase profitability. In this paper, we propose a machine learning approach to predict bank churn using a dataset of customer transactions and demographic information. We compare the performance of different machine learning models, including logistic regression, decision tree, random forest, and neural network, using evaluation metrics such as accuracy, precision, recall, and F1-score. Our results show that the random forest model outperforms other models with an accuracy of 87.5% and an F1-score of 0.87. Furthermore, we conduct feature selection and engineering to identify the most important features contributing to bank churn. Our findings suggest that factors such as customer age, account balance, and number of transactions are significant predictors of churn. Our research has important implications for banks to improve customer retention and reduce churn by leveraging machine learning techniques.

Keyword –ANN, K-Means, Random Forest, Support Vector Machine.