Explainable Creditworthiness Scoring using a Calibrated Multimodal Framework
DOI:
https://doi.org/10.29207/resti.v10i3.7507Keywords:
credit risk scoring, explainable AI (XAI), financial disclosure, multimodal credit modelingAbstract
This research presents an explainable, calibrated multimodal framework for creditworthiness scoring. It integrates financial ratios with narrative risk disclosures by using the 823 firm SEC (Securities and Exchange Commission,) filings. In this approach we have used a class-weighted, L2-regularized logistic regression within a unified pipeline. It produces calibrated probabilities via isotonic regression. We have assessed the performance across discrimination (ROC-AUC, PR-AUC), reliability (Brier, calibration curves), operating thresholds (F1, asymmetric costs), and business diagnostics. We have also included the Decision Curve Analysis to cover the pattern of net benefit across practical cutoffs. Our implementation covers an ablation study to verify multimodal gains over financial-only and text-only baselines. The present research findings state that the LightGBM + SHAP benchmark depicts better interpretability along with improved prediction accuracy. Thus. the study provide an useful insights towards effective governance and transparent system requirements which makes this suitable for effective financial risk management.
Downloads
References
Risk Management—Supervisory Guidance on Model Risk Management, https://www.federalreserve.gov/frrs/guidance/supervisory-guidance-on-model-risk-management.htm
Friedman, J.H.: Greedy function approximation: A gradient boosting machine. Annals of Statistics 29(5), 1189–1232 (2001), https://doi.org/10.1214/aos/1013203451
Ke, G., Meng, Q., Finley, T., et al.: Lightgbm: A highly efficient gradient boosting decision tree. In: Advances in Neural Information Processing Systems (2017), https://dl.acm.org/doi/10.5555/3294996.3295074
Breiman, L.: Statistical modeling: The two cultures. Statistical science 16(3), 199–231 (2001), https://doi.org/10.1214/ss/1009213726
Altman, E.I.: Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. The Journal of Finance 23(4), 589–609 (1968), https://doi.org/10.1111/j.1540-6261.1968.tb00843.x
Ohlson, J.A.: Financial ratios and the probabilistic prediction of bankruptcy. Journal of Accounting Research 18(1), 109–131 (1980), https://doi.org/10.2307/2490395
Shumway, T.: Forecasting bankruptcy more accurately: A simple hazard model. Journal of Business 74(1), 101–124 (2001), https://doi.org/10.1086/209665
Merton, R.C.: On the pricing of corporate debt: The risk structure of interest rates. Journal of Finance 29(2), 449–470 (1974), https://doi.org/10.2307/2978814
Campbell, J.Y., Hilscher, J., Szilagyi, J.: In search of distress risk. Journal of Finance 63(6), 2899–2939 (2008), https://doi.org/10.1111/j.1540-6261.2008.01416.x
Loughran, T., McDonald, B.: When is a liability not a liability? textual analysis, dictionaries, and 10-ks. Journal of Finance 66(1), 35–65 (2011), https://doi.org/10.1111/j.1540-6261.2010.01625.x
Li, Feng, Textual Analysis of Corporate Disclosures: A Survey of the Literature (February 7, 2011). Journal of Accounting Literature, Forthcoming, Available at SSRN: https://ssrn.com/abstract=1756926
U.S. Securities and Exchange Commission: Regulation S-K, Item 105: Risk Factors., https://www.sec.gov/rules/final/2019/33-10668.pdf (2019)
Ribeiro, M.T., Singh, S., Guestrin, C.: ”why should i trust you?”: Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD, pp. 1135–1144 (2016), https://dl.acm.org/doi/10.1145/2939672.2939778
Lundberg, S., Lee, S.-I.: A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems (2017), https://dl.acm.org/doi/10.5555/3295222.3295230
Lundberg, S.M., Erion, G., et al.: From local explanations to global understanding with explainable ai for trees. Nature Machine Intelligence 2, 56–67 (2020), https://doi.org/10.1038/s42256-019-0138-9
Roberts, D.R., Bahn, V., Ciuti, S., al.: Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure. Ecography 40(8), 913–929 (2017), https://doi.org/10.1111/ecog.02881
Vickers, A.J., Elkin, E.B.: Decision curve analysis: A novel method for evaluating prediction models. Medical Decision Making 26(6), 565–574 (2006), https://doi.org/10.1177/0272989X0629
Beaver, W.H.: Financial ratios as predictors of failure. Journal of Accounting Research 4, 71–111 (1966) Empirical Research in Accounting: Selected Studies, https://doi.org/10.2307/2490171
Altman, E.I.: Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. The Journal of Finance 23(4), 589–609 (1968), https://doi.org/10.2307/2978933
Hillegeist, S.A., Keating, E.K., Cram, D.P., Lundstedt, K.G.: Assessing the probability of bankruptcy. Review of Accounting Studies 9(1), 5–34 (2004), https://doi.org/10.1023/B:RAST.0000013627.90884.b7
Hand, D.J., Henley, W.E.: Statistical classification methods in consumer credit scoring: A review. Journal of the Royal Statistical Society: Series A 160(3), 523–541(1997), https://doi.org/10.1111/j.1467-985X.1997.00078.x
Lessmann, S., Baesens, B., Seow, H.-V., Thomas, L.: Benchmarking state-of-theart classification algorithms for credit scoring: An update of research. European Journal of Operational Research 247(1), 124–136 (2015), https://doi.org/10.1016/j.ejor.2015.05.030
Kogan, S., Levin, D., Routledge, B.R., Sagi, J.S., Smith, N.A.: Predicting risk from financial reports. In: Proceedings of the North American Chapter of the Association for Computational Linguistics (NAACL), pp. 272–280 (2009), https://doi.org/10.3115/1620754.1620794
Loughran, T., McDonald, B.: When is a liability not a liability? textual analysis, dictionaries, and 10-ks. The Journal of Finance 66(1), 35–65 (2011), https://doi.org/10.1111/j.1540-6261.2010.01625.x
Kravet, T., Muslu, V.: Textual risk disclosures and investors’ risk perceptions. Review of Accounting Studies 18(4), 1088–1122 (2013), https://doi.org/10.1007/s11142-013-9228-9
Lundberg, S.M., Lee, S.-I.: A unified approach to interpreting model predictions.In: Advances in Neural Information Processing Systems (NeurIPS), pp. 4765–4774 (2017), https://dl.acm.org/doi/10.5555/3295222.3295230
Niculescu-Mizil, A., Caruana, R.: Predicting good probabilities with supervised learning. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 625–632 (2005)., https://dl.acm.org/doi/10.1145/1102351.1102430
Zadrozny, B., Elkan, C.: Obtaining calibrated probability estimates from decision trees and naive bayesian classifiers. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 609–616 (2001), https://dl.acm.org/doi/10.5555/645530.655658
Vickers, A.J., Elkin, E.B.: Decision curve analysis: A novel method for evaluating prediction models. Medical Decision Making 26(6), 565–574 (2006), https://doi.org/10.1177/0272989X06295361
Siddiqi, N.: Intelligent Credit Scoring: Building and Implementing Better Credit Risk Scorecards Wiley, (2017), https://doi.org/10.1002/9781119282396.index
Federal Reserve Board, Revised Guidance on Model Risk Management (2026), https://www.federalreserve.gov/supervisionreg/srletters/SR2602.pdf
Kocoglu, E., & Ersoz, F. (2025). Explainable Artificial Intelligence (XAI) for Commercial Credit Limit Prediction Model: SHAP-LIME Comparison. In: Durakbasa, N.M., et al. (eds) Digitalization in Additive Manufacturing. ICPTDI 2024. Springer Tracts in Additive Manufacturing. Springer, Cham. https://doi.org/10.1007/978-3-031-84873-5_44
Gama, J., Zliobait˙e, I., Bifet, A., Pechenizkiy, M., Bouchachia, A.: A survey on ˇ concept drift adaptation. ACM Computing Surveys 46(4), 44–14437 (2014), https://doi.org/10.1145/2523813
U.S. Securities and Exchange Commission: SEC EDGAR Application Programming Interface (API)., https://www.sec.gov/edgar/sec-api-documentation. Accessed: 2025-08-20 (2025)
Altman, E.I.: Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. The journal of finance 23(4), 589–609 (1968), https://doi.org/10.1111/j.1540-6261.1968.tb00843.x
Beaver, W.H.: Financial ratios as predictors of failure. Journal of Accounting Research 4, 71–111 (1966), https://doi.org/10.2307/2490171
Sparck Jones, K.: A statistical interpretation of term specificity and its application in retrieval. Journal of Documentation 28(1), 11–21 (1972), https://doi.org/10.1108/eb026526
Hosmer, D.W., Lemeshow, S., Sturdivant, R.X.: Applied Logistic Regression. Wiley,(2013), https://doi.org/10.1002/9781118548387
Brier, G.W.: Verification of forecasts expressed in terms of probability. Monthly Weather Review 78(1), 1–3 (1950), http://dx.doi.org/10.1175/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2
Zadrozny, B., Elkan, C.: Transforming classifier scores into accurate multiclass probability estimates. In: Proceedings of the ACM SIGKDD, pp. 694–699 (2002), https://doi.org/10.1145/775047.775151
Zadrozny, B., Elkan, C.: Transforming classifier scores into accurate multiclass probability estimates. In: Proceedings of the 8th ACM SIGKDD, pp. 694–699 (2002), https://doi.org/10.1145/775047.775151
Niculescu-Mizil, A., Caruana, R.: Predicting good probabilities with supervised learning. In: ICML, pp. 625–632 (2005)
Vickers, A.J., Elkin, E.B.: Decision curve analysis: a novel method for evaluating prediction models. Medical Decision Making 26(6), 565–574 (2006), https://doi.org/10.1177/0272989x06295361
Committee on Supervision and Implementation: Model risk management. Technical report, Federal Reserve Board (2017). Supervisory Guidance SR 11-7, https://doi.org/10.1145/1102351.1102430
Downloads
Published
Issue
Section
License
Copyright in each article belongs to the author
- The author acknowledges that the RESTI Journal (System Engineering and Information Technology) is the first publisher to publish with a license Creative Commons Attribution 4.0 International License.
- Authors can enter writing separately, arrange the non-exclusive distribution of manuscripts that have been published in this journal into other versions (eg sent to the author's institutional repository, publication in a book, etc.), by acknowledging that the manuscript has been published for the first time in the RESTI (Rekayasa Sistem dan Teknologi Informasi) journal ;
