Explainable AI for Credit Risk Modeling Using SHAP and LIME
Keywords:
Explainable AI, SHAP, LIME, Credit Risk Modeling, Gradient Boosting, Regulatory ComplianceAbstract
Machine learning in credit risk modeling promotes financial decision transparency, accountability, and interpretability. Test SHAP and LIME's gradient-boosting credit scoring expertise. Comparing global and local explanation integrity, computational efficiency, and regulatory compliance under SR 11-7 model risk management supervisory recommendations using anonymised loan portfolio data. To comprehend high-dimensional credit data model accuracy-interpretability trade-offs, study feature attributions and local perturbation stability. SHAP provides coherent theoretical explanations, whereas LIME allows local stakeholder contact. XAI frameworks promote model governance, AI responsibility, and institutional trust in automated credit decisioning systems.
Downloads
References
S. M. Lundberg and S. Lee, "A unified approach to interpreting model predictions," in Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, CA, USA, 2017, pp. 4765–4774.
M. T. Ribeiro, S. Singh, and C. Guestrin, "Why should I trust you?" Explaining the predictions of any classifier, in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 2016, pp. 1135–1144.
Federal Reserve, "Supervisory Letter SR 11-7: Guidance on Model Risk Management," Board of Governors of the Federal Reserve System, Washington, D.C., USA, Apr. 4, 2011. [Online]. Available: https://www.federalreserve.gov/supervisionreg/srletters/sr1107.htm.
B. Hadji Misheva, J. Osterrieder, A. Hirsa, O. Kulkarni, and S. Fung Lin, "Explainable AI in credit risk management," arXiv preprint arXiv:2103.00949, Mar. 2021. [Online]. Available: https://arxiv.org/abs/2103.00949.
C. James, "Explainable AI in credit scoring: Improving transparency and accountability," ResearchGate, Dec. 2021.
S. B. Kotsiantis, D. Kanellopoulos, and P. Pintelas, "Data preprocessing for supervised learning," International Journal of Computer Science, vol. 1, no. 2, pp. 111–117, 2006.
G. Wali and C. Bulla, "Enhancing credit risk assessment with explainable AI: Integrating deep learning, SHAP, and game theory," ResearchGate, Jan. 2020.
M. Bücker, G. Szepannek, A. Gosiewska, and P. Biecek, "Transparency, auditability and explainability of machine learning models in credit scoring," arXiv preprint arXiv:2009.13384, Sep. 2020. [Online]. Available: https://arxiv.org/abs/2009.13384.
N. Llop Torrent, G. Visani, and E. Bagli, "PSD2 explainable AI model for credit scoring," arXiv preprint arXiv:2011.10367, Nov. 2020. [Online]. Available: https://arxiv.org/abs/2011.10367.
M. S. Reza, M. I. Mahmud, I. A. Abeer, and N. Ahmed, "Linear discriminant analysis in credit scoring: A transparent hybrid model approach," arXiv preprint arXiv:2412.04183, Dec. 2024. [Online]. Available: https://arxiv.org/abs/2412.04183.
R. Ajax, "Predictive modeling of credit risk using explainable AI (XAI)," ResearchGate, Jun. 2025.
J. Zhang, Y. Li, and L. Zhang, "A hybrid model for credit scoring using ensemble learning and explainable AI," Expert Systems with Applications, vol. 139, pp. 112–123, 2020.
S. M. Lundberg, "A unified approach to interpreting model predictions," arXiv preprint arXiv:1705.07874, May 2017. [Online]. Available: https://arxiv.org/abs/1705.07874.
M. T. Ribeiro, "Why should I trust you?" Explaining the predictions of any classifier, arXiv preprint arXiv:1602.04938, Feb. 2016. [Online]. Available: https://arxiv.org/abs/1602.04938.
J. P. Biecek and M. Bücker, "Model agnostic interpretability methods," arXiv preprint arXiv:1909.09223, Sep. 2019. [Online]. Available: https://arxiv.org/abs/1909.09223.
P. Biecek, "DALEX: Descriptive mAchine Learning EXplanations," arXiv preprint arXiv:1808.03355, Aug. 2018. [Online]. Available: https://arxiv.org/abs/1808.03355.
S. M. Lundberg and S. Lee, "SHAP (SHapley Additive exPlanations)," arXiv preprint arXiv:1705.07874, May 2017. [Online]. Available: https://arxiv.org/abs/1705.07874.
M. T. Ribeiro, S. Singh, and C. Guestrin, "LIME: Local Interpretable Model-agnostic Explanations," arXiv preprint arXiv:1602.04938, Feb. 2016. [Online]. Available: https://arxiv.org/abs/1602.04938.
Federal Reserve, "Supervisory Letter SR 11-7: Guidance on Model Risk Management," Board of Governors of the Federal Reserve System, Washington, D.C., USA, Apr. 4, 2011. [Online]. Available: https://www.federalreserve.gov/supervisionreg/srletters/sr1107.htm.
J. Zhang, Y. Li, and L. Zhang, "A hybrid model for credit scoring using ensemble learning and explainable AI," Expert Systems with Applications, vol. 139, pp. 112–123, 2020.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
