Regulatory Grade Fraud Detection using Explainable Artificial Intelligence with Auditable Decision Pathways and Empirical Validation on Banking Data
DOI:
https://doi.org/10.63282/3050-9262.IJAIDSML-V5I3P115Keywords:
Explainable Artificial Intelligence, Fraud Detection, Ensemble Learning, Banking Security, Regulatory ComplianceAbstract
Financial fraud has become a burning challenge on the world stage for bank institutions while calling for a systematic resolution in the form of accurate detection mechanisms with regulatory compliance. In this research, we propose explainable artificial intelligence (XAI) approaches for fraud detection in banking transactions with a focus on auditable decision pathways necessary for regulatory compliance. The ensemble deep learning approach incorporates Random Forest, Gradient Boosting, and stacking methods, along with SHAP values for model interpretability. Using real-world banking transaction datasets that are both genuine and fraudulent, our methodology uses isolation forest to detect anomalies and SMOTE to deal with class imbalance. We hypothesize that models enhanced by XAI achieve better detection performance while retaining interpretability for regulatory audits. Experimental results prove a detection accuracy rate of 98.7% while measuring with the metrics of 0.96 Precision and 0.94 Recall. Statistical validation demonstrates the validity of stacking ensemble methods together with explainability frameworks. Through discussions, we show how interpretable models allow for regulatory compliance while maintaining detection performance. The research contributes to improving regulatory compliance within financial services systems including explainability mechanisms which provide the transparency in decision pathways necessary for banking sector deployment and regulatory acceptance of fraud detection systems
References
[1] Ahmed, S., Lee, Y., Hyun, S. H., & Koo, I. (2019). Unsupervised machine learning-based detection of covert data integrity assault in smart grid networks utilizing isolation forest. IEEE Transactions on Information Forensics and Security, 14(10), 2765–2777. https://doi.org/10.1109/TIFS.2019.2902822
[2] Bhattacharyya, S., Jha, S., Tharakunnel, K., & Westland, J. C. (2011). Data mining for credit card fraud: A comparative study. Decision Support Systems, 50(3), 602–613. https://doi.org/10.1016/j.dss.2010.08.008
[3] Dal Pozzolo, A., Caelen, O., Le Borgne, Y.-A., Waterschoot, S., & Bontempi, G. (2014). Learned lessons in credit card fraud detection from a practitioner perspective. Expert Systems with Applications, 41(10), 4915–4928. https://doi.org/10.1016/j.eswa.2014.02.026
[4] Ge, D., Gu, J., Chang, S., & Cai, J. (2020). Credit card fraud detection using LightGBM model. In Proceedings of the 2020 International Conference on E-Commerce and Internet Technology (ECIT) (pp. 232–236). IEEE. https://doi.org/10.1109/ECIT50008.2020.00060
[5] Ghevariya, R., Desai, R., Bohara, M. H., & Garg, D. (2021). Credit card fraud detection using local outlier factor and isolation forest algorithms: A complete analysis. In 2021 5th International Conference on Electronics, Communication and Aerospace Technology (ICECA) (pp. 1679–1685). IEEE. https://doi.org/10.1109/ICECA52323.2021.9675971
[6] Islam, M. A., Uddin, M. A., Aryal, S., & Stea, G. (2023). An ensemble learning approach for anomaly detection in credit card data with imbalanced and overlapped classes. Journal of Information Security and Applications, 78, 103618. https://doi.org/10.1016/j.jisa.2023.103618
[7] Jiang, C., Song, J., Liu, G., Zheng, L., & Luan, W. (2018). Credit card fraud detection: A novel approach using aggregation strategy and feedback mechanism. IEEE Internet of Things Journal, 5(5), 3637–3647. https://doi.org/10.1109/JIOT.2018.2816007
[8] Kewei, X., Peng, B., Jiang, Y., & Lu, T. (2021). A hybrid deep learning model for online fraud detection. In Proceedings of the 2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE) (pp. 431–434). IEEE. https://doi.org/10.1109/ICCECE51280.2021.9342110
[9] Mienye, I. D., & Sun, Y. (2023). A deep learning ensemble with data resampling for credit card fraud detection. IEEE Access, 11, 30628–30638. https://doi.org/10.1109/ACCESS.2023.3262020
[10] Nguyen, N., et al. (2022). A proposed model for card fraud detection based on CatBoost and deep neural network. IEEE Access, 10, 96852–96861. https://doi.org/10.1109/ACCESS.2022.3205416
[11] Pumsirirat, A., & Yan, L. (2018). Credit card fraud detection using deep learning based on auto-encoder and restricted Boltzmann machine. International Journal of Advanced Computer Science and Applications, 9(1). https://doi.org/10.14569/IJACSA.2018.090103
[12] Randhawa, K., Loo, C. K., Seera, M., Lim, C. P., & Nandi, A. K. (2018). Credit card fraud detection using AdaBoost and majority voting. IEEE Access, 6, 14277–14284. https://doi.org/10.1109/ACCESS.2018.2806420
[13] Sharma, M. A., Raj, B. R. G., Ramamurthy, B., & Bhaskar, R. H. (2022). Credit card fraud detection using deep learning based on auto-encoder. ITM Web of Conferences, 50, 01001. https://doi.org/10.1051/itmconf/20225001001
[14] Thudumu, S., Branch, P., Jin, J., & others. (2020). A comprehensive survey of anomaly detection techniques for high dimensional big data. Journal of Big Data, 7(42). https://doi.org/10.1186/s40537-020-00320
[15] Veigas, K. C., Regulagadda, D. S., & Kokatnoor, S. A. (2021). Optimized stacking ensemble (OSE) for credit card fraud detection using synthetic minority oversampling model. Indian Journal of Science and Technology, 14(32), 2607–2615. https://doi.org/10.17485/IJST/v14i32.807
[16] Zareapoor, M., & Shamsolmoali, P. (2015). Application of credit card fraud detection: Based on bagging ensemble classifier. Procedia Computer Science, 48, 679–685. https://doi.org/10.1016/j.procs.2015.04.201
[17] Gunda, S. K. G. (2023). The Future of Software Development and the Expanding Role of ML Models. International Journal of Emerging Research in Engineering and Technology, 4(2), 126-129. https://doi.org/10.63282/3050-922X.IJERET-V4I2P113
