AN EXPLAINABLE AI FRAMEWORK FOR INTERPRETABLE AND RELIABLE FRAUD DETECTION IN FINANCIAL SYSTEMS

International Journal of Computer Science (IJCS) Published by SK Research Group of Companies (SKRGC)

Abstract

Fraud detection has become a critical challenge in modern financial systems due to the rapid growth of digital transactions. Although machine learning models have demonstrated high accuracy in detecting fraudulent activities, their black-box nature limits transparency and hinders trust in real-world applications. This paper proposes an Explainable Artificial Intelligence (XAI)-based framework to enhance the interpretability of fraud detection models without compromising predictive performance. The proposed approach integrates advanced machine learning classifiers with post-hoc explanation techniques, including Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive explanations (SHAP), to generate both local and global insights into model decisions. Experimental evaluation on real-world datasets shows that the framework achieves high detection accuracy while significantly improving transparency, trustworthiness, and regulatory compliance. The results demonstrate that XAI plays a vital role in bridging the gap between model performance and human interpretability in fraud detection systems.

References

1. A. Adadi and M. Berrada, “Peeking inside the black-box: A survey on explainable artificial intelligence (XAI),” IEEE Access, vol. 6, pp. 52138–52160, 2018.
2. M. T. Ribeiro, S. Singh, and C. Guestrin, “Why should I trust you? Explaining the predictions of any classifier,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (KDD), San Francisco, CA, USA, 2016, pp. 1135–1144.
3. S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” in Proc. 31st Int. Conf. Neural Information Processing Systems (NeurIPS), 2017, pp. 4765–4774.
4. C. Molnar, *Interpretable Machine Learning*, 2nd ed. Leanpub, 2022.
5. F. Doshi-Velez and B. Kim, “Towards a rigorous science of interpretable machine learning,” arXiv preprint arXiv:1702.08608, 2017.

Keywords

Explainable Artificial Intelligence (XAI), Fraud Detection, Machine Learning, Model Interpretability, SHAP, LIME, Financial Security.