Transparent Deep Learning for Credit Default Analysis: An Explainable ANN Framework Combining SHAP and LIME
Keywords:
Credit Default Prediction, Explainable Artificial Intelligence, Artificial Neural Networks, SHAP, LIMEAbstract
This study introduces a transparent deep learning framework for credit default analysis that integrates Artificial Neural Networks (ANN) with dual interpretability mechanisms SHapley Additive Explanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME). Using the Default of Credit Card Clients dataset from the UCI Machine Learning Repository, the research develops an optimized model that combines predictive precision with explanatory transparency. The ANN model achieved an accuracy of 81.8% and an AUC of 0.77, outperforming conventional classifiers such as XGBoost and LightGBM while maintaining interpretive clarity. The hybrid SHAP–LIME configuration provides both global and local explanations, identifying repayment status (PAY_0), billing amount (BILL_AMT1), and credit limit (LIMIT_BAL) as the most influential predictors. Empirical findings confirm that interpretability enhances trust, auditability, and regulatory alignment without sacrificing statistical performance. The framework offers a methodological contribution to transparent financial modeling, bridging the gap between algorithmic precision and human interpretive accountability. It advances the paradigm of responsible credit risk management by transforming black-box neural architectures into auditable, evidence-based decision tools for financial institutions
Downloads
References
Ananda, S., Negara, B. S., Irsyad, M., Jasril, J., & Iskandar, I. (2025). Applying Local Interpretable Model-Agnostic Explanations (Lime) For Interpretable Deep Learning In Lung Disease Detection. Journal Of Artificial Intelligence And Software Engineering, 5(2), 686-696. http://dx.doi.org/10.30811/jaise.v5i2.7042.
Arif, E., Suherman, I., & Widodo, A. P. (2025). Revolusi Prediksi Saham: Pemanfaatan Machine Learning Dan Analisis Sentimen Dalam Dunia Keuangan. Greenbook Publisher.
Bhandary, S. (2025). A Deep Learning Framework For Default Prediction. Journal Of Risk And Financial Management, 18(1), 23. Https://Www.Mdpi.Com/1911-8074/18/1/23
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). Smote: Synthetic Minority Over-Sampling Technique. Journal Of Artificial Intelligence Research, 16(1), 321–357. Https://Doi.Org/10.1613/Jair.953
Chen, T., & Guestrin, C. (2016). Xgboost: A Scalable Tree Boosting System. In Proceedings Of The 22nd Acm Sigkdd International Conference On Knowledge Discovery And Data Mining (Pp. 785–794). Acm. Https://Doi.Org/10.1145/2939672.2939785 .
Coussement, K., & Benoit, D. F. (2021). Interpretable Data Science For Decision Making. Decision Support Systems, 150, 113664. https://doi.org/10.1016/j.dss.2021.113664.
Damanik, N., & Liu, C. M. (2025). Towards Explainable And Balanced Federated Learning: A Neural Network Approach For Multi-Client Fraud Detection. International Journal Of Advanced Computer Science & Applications, 16(8). https://doi.org/10.14569/ijacsa.2025.0160837.
Efunniyi, C. P., Abhulimen, A. O., Obiki-Osafiele, A. N., Osundare, O. S., Agu, E. E., & Adeniran, I. A. (2024). Strengthening Corporate Governance And Financial Compliance: Enhancing Accountability And Transparency. Finance & Accounting Research Journal, 6(8), 1597-1616. https://doi.org/10.51594/farj.v6i8.1509.
Heldt, E. C., & Herzog, L. (2022). The Limits Of Transparency: Expert Knowledge And Meaningful Accountability In Central Banking. Government And Opposition, 57(2), 217-232. https://doi.org/10.1017/gov.2020.36.
Herbinger, J., Wright, M. N., Nagler, T., Bischl, B., & Casalicchio, G. (2024). Decomposing Global Feature Effects Based On Feature Interactions. Journal Of Machine Learning Research, 25(381), 1-65.
Hossain, N. (2023). A Comparative Analysis Of Conventional And Modern Methods Of Credit Risk Assessment In Financial Institutions: Implications For Micro, Small And Medium Enterprises (Msmes). http://hdl.handle.net/10361/22883.
Lendingtree. (2025, August). Credit Card Debt Statistics 2025.
Lu, H., & Wu, Z. (2025). Revisiting Intelligent Audit From A Data Science Perspective. Neurocomputing, 129431. https://doi.org/10.1016/j.neucom.2025.129431.
Malandreniotis, D. (2024). Probabilistic Forecasting Models For Multidimensional Financial Time-Series With Applications To Systematic Portfolio Management (Doctoral Dissertation, Ucl (University College London)).
Mohanarajesh, K. (2024). Investigate Methods For Visualizing The Decision-Making Processes Of A Complex Ai System, Making Them More Understandable And Trustworthy In Financial Data Analysis.
Nagaraj, S. K. S. (2025). A Study On Credit Default Prediction Using Hybrid Ai Models Combining Neural Architectures And Econometric Features. International Journal Of Emerging Research In Engineering And Technology, 6(2), 81-88. https://doi.org/10.63282/3050-922X.IJERET-V6I2P110.
Oyasiji, O., Okesiji, A., Imediegwu, C. C., Elebe, O., & Filani, O. M. (2023). Ethical Ai In Financial Decision-Making: Transparency, Bias, And Regulation. International Journal Of Scientific Research In Computer Science, Engineering And Information Technology, 9(5), 453-471.
Park, M. (2025). Enhancing Esg Risk Assessment With Litigation Signals: A Legal-Ai Hybrid Approach For Detecting Latent Risks. Systems, 13(9), 783. https://doi.org/10.3390/systems13090783.
Rudin, C., Chen, C., Chen, Z., Huang, H., Semenova, L., & Zhong, C. (2022). Interpretable Machine Learning: Fundamental Principles And 10 Grand Challenges. Statistic Surveys, 16, 1-85. https://doi.org/10.1214/21-SS133
Si, J., Cheng, W. Y., Cooper, M., & Krishnan, R. G. (2024). Interpretabnet: Distilling Predictive Signals From Tabular Data By Salient Feature Interpretation. Arxiv Preprint Arxiv:2406.00426. https://doi.org/10.48550/arXiv.2406.00426.
Siraj, M. L., Syarifuddin, S., Tadampali, A. C. T., Zainal, H., & Mahmud, R. (2024). Understanding Financial Risk Dynamics: Systematic Literature Review Inquiry Into Credit, Market, And Operational Risks:(A Long-Life Lesson From Global Perspective To Indonesia Market Financial Strategy). Atestasi: Jurnal Ilmiah Akuntansi, 7(2), 1186-1213. https://doi.org/10.57178/atestasi.v7i2.927.
Smith, H. K. (2025). Balancing Class Distributions For Explainable Ai Models In Lending Decisions.
Source: Ycharts. (2025, July). U.S. Credit Card Accounts Late By 90 Days. Https://Ycharts.Com/Indicators/Us_Credit_Card_Accounts_Late_By_90_Days
Talaat, F. M., Aljadani, A., Badawy, M., & Elhosseini, M. (2024). Toward Interpretable Credit Scoring: Integrating Explainable Artificial Intelligence With Deep Learning For Credit Card Default Prediction. Neural Computing And Applications, 36(9), 4847-4865. https://doi.org/10.1007/s00521-023-09232-2.
Tursunalieva, A., Alexander, D. L., Dunne, R., Li, J., Riera, L., & Zhao, Y. (2024). Making Sense Of Machine Learning: A Review Of Interpretation Techniques And Their Applications. Applied Sciences, 14(2), 496. https://doi.org/10.3390/app14020496.
Wallethub. (2025, July). Credit Card Charge-Off And Delinquency Statistics. Https://Wallethub.Com/Edu/Cc/Credit-Card-Charge-Off-Delinquency-Statistics/25536.
Wallethub. (2025, June). Credit Card Charge-Off And Delinquency Statistics. Https://Wallethub.Com/Edu/Cc/Credit-Card-Charge-Off-Delinquency-Statistics/25536
Wang, H. (2021). Credit Risk Management Of Consumer Finance Based On Big Data. Mobile Information Systems, 2021(1), 8189255.
Wang, Z., & Liang, J. (2024). Comparative Analysis Of Interpretability Techniques For Feature Importance In Credit Risk Assessment. Spectrum Of Research, 4(2).
Yang, H., Li, C., & Zhao, J. (2025). Credit Scoring Through Interpretable Ensemble Learning. Arxiv Preprint Arxiv:2505.20815. https://doi.org/10.48550/arXiv.2505.20815.
Yates, L. A., Aandahl, Z., Richards, S. A., & Brook, B. W. (2023). Cross Validation For Model Selection: A Review With Examples From Ecology. Ecological Monographs, 93(1), E1557. https://doi.org/10.1002/ecm.1557.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Norma Zuhrotul Hayati, Anggyi Trisnawan Putra (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
