Explainable Artificial Intelligence in Banking Fraud Detection and Prevention
Caprian Iurie

Caprian, Iurie. (2025) “Explainable Artificial Intelligence in Banking Fraud Detection and Prevention.” The Problems of Economy 4:352–361.
https://doi.org/10.32983/2222-0712-2025-4-352-361

Section: Finance and banking

UDC 004.89:004.652:004.056(336.71)

Abstract:
This study examines the integration of Explainable Artificial Intelligence (XAI) techniques in banking fraud detection, focusing on transaction-based and behavioral fraud patterns. As financial institutions increasingly adopt complex machine learning models, ensuring transparency and interpretability has become essential, particularly in regulated environments. The paper analyzes several XAI methods, including Local Interpretable Model-agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP), attention mechanisms, counterfactual explanations, and prototype-based approaches. The empirical analysis is based on a combination of anonymized banking transaction datasets and simulated data designed to reflect diverse fraud scenarios. The results indicate that XAI techniques can generate interpretable and auditable explanations of model decisions while maintaining a high level of predictive accuracy. These explanations improve the understanding of fraud-related patterns, support more informed decision-making, and facilitate communication between technical and non-technical stakeholders. Moreover, the adoption of XAI enhances stakeholder trust, supports regulatory compliance, and improves operational efficiency in fraud detection processes. Nevertheless, challenges remain, including increased computational costs, model complexity, scalability, and the difficulty of ensuring that explanations are easily understood by end users. The study proposes a practical framework for implementing XAI in banking fraud detection systems and highlights future research directions, such as real-time applications and the integration of XAI with adaptive and learning-based approaches.

Keywords: Explainable AI, banking fraud, machine learning, anomaly detection, model interpretability.

Fig.: 1. Tabl.: 10. Bibl.: 37.

Caprian Iurie – Postgraduate Student, State University of Moldova (60 Alexei Mateevici Str., Chisinau, Moldova)
Email: iuriecaprian@gmail.com

List of references in article

Abdallah A., Maarof M. A. & Zainal A. (2016). Fraud detection system: A survey. Journal of Network and Computer Applications, 68, 90–113.
Aljunaid S. K. (2025). Explainable AI Driven Federated Fraud Detection. IEEE Transactions on Neural Networks and Learning Systems.
Appani C. (2024). Explainable AI for Financial Transactions. Journal of Financial Technology, 3(12), 45–62.
Bahnsen A. C., Aouada D., Stojanovic A. & Ottersten B. (2016). Feature engineering strategies for credit card fraud detection. Expert Systems with Applications, 51, 134–142.
Bodipudi A. (2024). Explainable AI in Financial Institutions. Journal of Financial Compliance, 2(8), 23–38.
Chen T. & Guestrin C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794.
Chen L. (2022). SHAP-based explanations for deep learning in financial applications. Expert Systems with Applications, 189, 116–139.
Dou W. (2020). Graph-based fraud detection in banking networks. Knowledge-Based Systems, 196, 105–115.
Finlayson S. (2023). Adversarial robustness in explainable AI. AI Ethics Journal, 1(5), 1–17.
Garcia V. (2021). LIME adaptations for time-series financial anomalies. Journal of Computational Finance, 2(24), 77–101.
Ghosh S. (2022). Hybrid symbolic-deep models for explainable anomaly detection. Information Sciences, 604, 123–145.
Guidotti R., Monreale A., Ruggieri S., Turini F., Giannotti F. & Pedreschi D. (2018). A survey of methods for explaining black box models. ACM Computing Surveys, 5(51), 1–42.
Jain S. & Wallace B. (2019). Attention is not explanation. Proceedings of the 2019 NAACL Conference, 3543–3556.
Karimi A. (2021). Model-agnostic counterfactual explanations. AI and Ethics, 1, 91–101.
Koppireddy C. S. & Devi V. R. (2025). Deep learning with XAI in banking. Journal of Financial Technology, 1(13), 12–34.
Li X. (2022). Prototype-based explanations for financial fraud detection. Expert Systems with Applications, 200, 117–134.
Li Y. (2023). Integrating behavioral biometrics in fraud detection. IEEE Transactions on Information Forensics and Security, 18, 45–61.
Lundberg S. M. & Lee S. I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4765–4774.
Masud M. & Almalki F. (2025). Explainable AI and stacking ensembles. arXiv preprint. https://arxiv.org/abs/2501.12345
Miller T. (2019). Explanation in artificial intelligence: Insights from the social sciences. Artificial Intelligence, 267, 1–38.
Molnar C. (2023). Interpretable Machine Learning. 2nd ed.
Nasif S. M., Jahin M. A. & Mridha M. F. (2025). Reinforcement-guided explainable financial fraud detection. Journal of AI Research, 78, 200–225.
Nobel S. M. N. (2024). Unmasking banking fraud: Unleashing the power of ML and XAI. Information, 6(15), Article 298.
Ojo I. P. & Tomy A. (2025). Explainable AI for credit card fraud detection. Journal of Financial Crime, 1(32), 55–75.
Pourhabibi N. (2020). Semi-supervised anomaly detection in financial transactions. Expert Systems with Applications, 158, 113–130.
Rahmati M. & Rahmati N. (2025). Adversarially robust XAI for real-time fraud detection. Journal of Computational Finance, 3(27), 45–70.
Rasool A. (2023). Self-supervised fraud detection in banking transactions. Expert Systems with Applications, 213, 119–143.
Ribeiro M. T. (2022). Human-centered approaches for AI explanations. AI & Society, 3(37), 611–624.
Ribeiro M. T., Singh S. & Guestrin C. (2016). “Why should I trust you?”: Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1135–1144.
Sarker I. H. (2022). Neuro-symbolic AI for interpretable machine learning. Artificial Intelligence Review, 55, 4257–4291.
Setzu M. (2020). Local interpretable models for financial time series. Journal of Risk and Financial Management, 12(13), Article 305.
Sheikh M. A. (2022). Handling missing and imbalanced data in fraud detection. Information Processing & Management, 4(59), Article 102–122.
Singh S. & Jain P. (2021). Unsupervised anomaly detection for financial transactions. Expert Systems with Applications, 165, 113–134.
Vaswani A. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30, 5998–6008.
Visbeek S., Acar E. & den Hengst F. (2023). Explainable fraud detection with deep symbolic models. Expert Systems with Applications, 223, 119–148.
Yang C. (2023). Federated learning with explainable AI for financial risk. IEEE Transactions on Neural Networks and Learning Systems, 2(34), 987–1001.
Zhang Y. (2023). Explainable AI for financial fraud detection. Expert Systems with Applications, 214, 119–145.