Comparative Analysis of Machine Learning Algorithms for Bank Customer Churn Prediction

Karthika Gopalakrishnan

Abstract: This paper investigates the application of Machine Learning (ML) algorithms for predicting customer churn in the banking industry. Customer churn, signifying customer defection to competitors, stands as a significant hurdle to bank growth and profitability. By proactively identifying at-risk customers, banks can implement retention strategies to mitigate churn. We present a case study employing a bank customer churn dataset. Four prominent ML algorithms - Random Forest, Support Vector Machine (SVM), Decision Trees, and XGBoost - are utilized to predict churn. A comparative analysis is conducted to assess the performance of these algorithms using metrics like accuracy, precision, recall, and F1-score. The results emphasize the efficacy of ML in churn prediction compared to traditional methods. We conclude by outlining potential areas for future research.

Keywords: Churn Prediction, SVM, Banking Industry, XGBoost, Decision Trees, Machine Learning Automation

How to Cite?: Karthika Gopalakrishnan, "Comparative Analysis of Machine Learning Algorithms for Bank Customer Churn Prediction", Volume 12 Issue 6, June 2023, International Journal of Science and Research (IJSR), Pages: 2980-2983, https://www.ijsr.net/getabstract.php?paperid=SR24531143837, DOI: https://dx.doi.org/10.21275/SR24531143837