An Ensemble Machine Learning Approach for Financial Fraud Detection in Banking Systems

Richard Chafukira Phiri; Confidence Chigozirim Olumba; Simon Onuwa Agbonifo; Uchechi Joyce Nneji; Benjamin Chiemeka Opara; Miracle Ugomma Anunobi; Precious; Mojolaoluwa Ojo; Gladys Chinyere Olumba

doi:10.56201/ijbfr.vol.12.no2.2026.pg1.32

An Ensemble Machine Learning Approach for Financial Fraud Detection in Banking Systems

Richard Chafukira Phiri, Confidence Chigozirim Olumba, Simon Onuwa Agbonifo, Uchechi Joyce Nneji, Benjamin Chiemeka Opara, Miracle Ugomma Anunobi, Precious, Mojolaoluwa Ojo, Gladys Chinyere Olumba, .

Abstract

Financial fraud detection is a critical challenge in modern banking systems, where fraudulent transactions represent less than 0.13% of total transactions, creating severe class imbalance. Traditional rule-based systems struggle to adapt to evolving fraud patterns, necessitating machine learning approaches that can learn complex patterns from historical data while handling extreme class imbalance. This study implements and evaluates three feature selection techniques Minimum Redundancy-Maximum Relevance , Multi Spatially Uniform ReliefF (MultiSURF), and Hilbert-Schmidt Independence Criterion combined with eight optimized machine learning classifiers including Support Vector Machine , Logistic Regression (LR), K-Nearest Neighbors , Decision Tree (DT), AdaBoost , Bagging , Stacking , and Voting classifiers. The financial payment services fraud dataset containing 6,362,620 transactions was preprocessed using under sampling for class balancing and Standard Scaler for normalization. GridSearchCV with 5-fold cross-validation was employed for hyperparameter optimization across 32 experimental configurations. Experimental results demonstrate that Bagging classifier without feature selection achieves the highest performance with 99.51% accuracy, 99.15% precision, 99.88% recall, 99.51% F1-score, and 99.92% ROC-AUC in 10.67 seconds training time. Among feature selection methods, MultiSURF maintains competitive performance, while mRMR and HSIC show performance degradation. Ensemble methods consistently outperform single classifiers across all experimental scenarios. This study provides empirical evidence that for fraud detection with well-engineered features in low-dimensional spaces, ensemble methods yield optimal results. The undersampling strategy proves effective for handling class imbalance while maintaining computational efficiency. The findings demonstrating that feature selection is not always beneficial when original features are already highly relevant.

Keywords

Financial Fraud DetectionEnsemble LearningFeature Selection TechniquesBaggingMachine Learning

References

Almazroi, A. A., & Ayub, N. (2023). Online payment fraud detection model using machine learning techniques. IEEE Access, 11, 137188–137203. https://doi.org/10.1109/ACCESS.2023.3339226 Banirostam, H., Banirostam, T., Pedram, M. M., & Rahmani, A. M. (2023). A model to detect the fraud of electronic payment card transactions based on stream processing in big data. Journal of Signal Processing Systems, 95(12), 1469–1484. https://doi.org/10.1007/s11265-023-01903-6 Choi, D., & Lee, K. (n.d.). Machine learning–based approach to financial fraud detection process in mobile payment system. Dalal, S., Seth, B., Radulescu, M., Secara, C., & Tolea, C. (2022). Predicting fraud in financial payment services through optimized hyper-parameter-tuned XGBoost model. Mathematics, 10(24), 4679. https://doi.org/10.3390/math10244679 David, G., et al. (2024). SynoBoost-LuminoFeatML for financial fraud prediction. World Scientific Proceedings, 354–375. https://doi.org/10.1142/WSN198(2024)354-375 Faccia, A. (2023). National payment switches and the power of cognitive computing against fintech fraud. Big Data and Cognitive Computing, 7(2), 76. https://doi.org/10.3390/bdcc7020076 Hajek, P., Abedin, M. Z., & Sivarajah, U. (2023). Fraud detection in mobile payment systems using an XGBoost-based framework. Information Systems Frontiers, 25(5), 1985–2003. https://doi.org/10.1007/s10796-022-10346-6 Kovács, L., & David, S. (2016). Fraud risk in electronic payment transactions. Journal of Money Laundering Control, 19(2), 148–157. https://doi.org/10.1108/JMLC-09-2015-0039 Pozzolo, A. D., Caelen, O., Johnson, R. A., & Bontempi, G. (2015). Calibrating probability with undersampling for unbalanced classification. In Proceedings of the IEEE Symposium Series on Computational Intelligence (pp. 159–166). IEEE. https://doi.org/10.1109/SSCI.2015.33 Sakharova, I. (2012). Payment card fraud: Challenges and solutions. In Proceedings of the IEEE International Conference on Intelligence and Security Informatics (pp. 227–234). IEEE. https://doi.org/10.1109/ISI.2012.6284315 Seera, M., Lim, C. P., Kumar, A., Dhamotharan, L., & Tan, K. H. (2024). An intelligent payment card fraud detection system. Annals of Operations Research, 334(1), 445–467. https://doi.org/10.1007/s10479-021-04149-2 Urbanowicz, R. J., Meeker, M., La Cava, W., Olson, R. S., & Moore, J. H. (2018). Relief-based feature selection: Introduction and review. Journal of Biomedical Informatics, 85, 189– 203. https://doi.org/10.1016/j.jbi.2018.07.014 Vanini, P., Rossi, S., Zvizdic, E., & Domenig, T. (2023). Online payment fraud: From anomaly detection to risk management. Financial Innovation, 9(1), 66. https://doi.org/10.1186/s40854-023-00470-w

An Ensemble Machine Learning Approach for Financial Fraud Detection in Banking Systems

Abstract

Keywords

References

More Articles from IIARD INTERNATIONAL JOURNAL OF BANKING AND FINANCE RESEARCH