International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Early Bank Customer Churn Risk Prediction and Decision Support System using Machine Learning |
|---|---|
| ABSTRACT | Customer churn prediction has become an important task in the banking sector, as it helps reduce revenue loss and improve customer retention. In this work, a machine learning-based churn prediction and decision support system is developed using the publicly available BankChurners dataset, which contains over 10,000 customer records. Data preprocessing techniques were applied, and SMOTE was used to address class imbalance in the dataset. The data was divided into 80% for training and 20% for testing. Multiple machine learning models were evaluated, among which XGBoost showed the best performance. It achieved an accuracy of 97%, recall of 90%, and an AUC score of 0.99, making it effective in identifying customers who are likely to churn. The system also provides probability-based risk segmentation and includes a simplified Value at Risk (VaR) approach to estimate potential financial loss. In addition, a simulation-based decision support module is introduced to analyze different retention strategies, such as customer engagement programs and transaction-based incentives. A Streamlit dashboard was developed to enable real-time interaction and analysis. Overall, the proposed system supports proactive and data-driven decision-making for customer retention in banking applications. |
| AUTHOR | P. NEHA SRI, M. RUSHMIKA, S. KIRAN KUMAR, K. SRI VIJAYA UG Students, Department of Information Technology, Prasad V Potluri Siddhartha Institute of Technology, Vijayawada, India Assistant Professor, Department of Information Technology, Prasad V Potluri Siddhartha Institute of Technology, Vijayawada, India |
| VOLUME | 182 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1403135 |
| pdf/135_Early Bank Customer Churn Risk Prediction and Decision Support System using Machine Learning.pdf | |
| KEYWORDS | |
| References | [1] A. Gulati, et al., “Bank Customer Churn Prediction Using Machine Learning: A Comparative Study with SMOTE-Based Class Balancing,” Proc. IEEE ICCES, 2025. [2] H. Jin, “Bank Customer Churn Prediction Based on Machine Learning Models,” Proc. 9th Int. Conf. Economic Management and Green Development, 2025. doi: 10.54254/2754-1169/2025.LH23973. [3] “Customer Churn Prediction Model using Machine Learning,” International Journal of Computer Science Trends and Technology, 2023. [4] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: Synthetic Minority Over-sampling Technique,” Journal of Artificial Intelligence Research, vol. 16, pp. 321–357, 2002. [5] T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” Proc. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794, 2016. [6] F. Pedregosa, et al., “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011. [7] C. Molnar, Interpretable Machine Learning, 2nd ed., 2022. [Online]. Available: https://christophm.github.io/interpretable-ml-book/ [8] “BankChurners Dataset,” Kaggle, 2024. [Online]. Available: https://www.kaggle.com/datasets/sakshigoyal7/credit-card-customers |
