A Panel-Based Dynamic Credit Rating Proxy Model Using Altman Z-Scores: Evidence from Bangladesh
Authors
Associate Professor & Head, Department of Business Administration, RTM Al-Kabir Technical University, TB Gate, East Shahi Eidgah, Sylhet-3100, Sylhet, Bangladesh. (Bangladesh)
Article Information
DOI: 10.51583/IJLTEMAS.2026.151000067
Subject Category: Business
Volume/Issue: 15/10 | Page No: 809-829
Publication Timeline
Submitted: 2026-10-15
Accepted: 2026-10-20
Published: 2026-11-07
Abstract
This study develops a panel-based Dynamic Credit Rating Proxy Index (DCRPI) by integrating financial distress indicators, rating persistence, migration behavior, and machine learning-derived feature importance to improve corporate credit risk assessment in Bangladesh. Using panel data for 40 publicly listed Bangladeshi firms (2021–2025), the study estimates an ordered logit model using current and lagged Altman Z-scores, changes in financial distress, lagged ratings, and rating migration. Random Forest and Extreme Gradient Boosting (XGBoost) are employed to estimate feature importance and construct the DCRPI. The framework is validated using performance measures, 10-fold cross-validation, confusion matrix analysis, robustness tests, and panel diagnostic assessments. Altman Z-scores are positively associated with credit ratings, while machine learning results indicate that lagged ratings and migration dynamics are more influential than contemporaneous financial distress indicators. Random Forest and XGBoost achieve predictive accuracies above 95%, outperforming conventional econometric models.
The DCRPI achieves comparable predictive performance with greater interpretability. The study introduces an interpretable hybrid DCRPI integrating financial distress indicators, dynamic rating behavior, and machine learning feature importance. It contributes to explainable hybrid credit risk modeling and provides a practical proxy for corporate credit assessment in emerging markets with limited formal credit ratings. The proposed DCRPI provides financial institutions, investors, regulators, and policymakers with a transparent tool for assessing corporate creditworthiness where formal ratings are limited. The analysis covers listed Bangladeshi firms during 2021–2025. Future research should examine larger samples, additional emerging economies, and alternative machine learning techniques. However, the study contributes to the literature by introducing a hybrid panel-based dynamic proxy model that integrates machine learning and accounting-based distress measures within an emerging market context.
Keywords
Altman Z-score, credit rating, Random Forest, XGBoost, machine learning
This article is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
Downloads
References
1. Adadi, A., & Berrada, M. (2018). Peeking inside the black-box: A survey on explainable artificial intelligence (XAI). IEEE Access, 6, 52138–52160. https://doi.org/10.1109/ACCESS.2018.2870052 [Google Scholar] [Crossref]
2. Allen, L., Bali, T. G., & Tang, Y. (2013). Does systemic risk in the financial sector predict future economic downturns? The Review of Financial Studies, 25(10), 3000–3036. https://doi.org/10.1093/rfs/hhs094 [Google Scholar] [Crossref]
3. Altman, E. I. (1968). Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. The Journal of Finance, 23(4), 589–609. https://doi.org/10.1111/j.1540-6261.1968.tb00843.x [Google Scholar] [Crossref]
4. Altman, E. I., Hartzell, J., & Peck, M. (1995). Emerging market corporate bonds: A scoring system. Salomon Brothers Inc., New York. [Google Scholar] [Crossref]
5. Altman, E. I., Iwanicz-Drozdowska, M., Laitinen, E. K., & Suvas, A. (2017). Financial distress prediction in an international context: A review and empirical analysis of Altman’s Z-score model. Journal of International Financial Management & Accounting, 28(2), 131–171. https://doi.org/10.1111/jifm.12053 [Google Scholar] [Crossref]
6. Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., García, S., Gil-López, S., Molina, D., Benjamins, R., Chatila, R., & Herrera, F. (2020). Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion, 58, 82–115. https://doi.org/10.1016/j.inffus.2019.12.012 [Google Scholar] [Crossref]
7. Bangia, A., Diebold, F. X., Kronimus, A., Schagen, C., & Schuermann, T. (2002). Ratings migration and the business cycle, with application to credit portfolio stress testing. Journal of Banking & Finance, 26(2–3), 445–474. https://doi.org/10.1016/S0378-4266(01)00229-1 [Google Scholar] [Crossref]
8. Barboza, F., Kimura, H., & Altman, E. (2017). Machine learning models and bankruptcy prediction. Expert Systems with Applications, 83, 405–417. https://doi.org/10.1016/j.eswa.2017.04.006 [Google Scholar] [Crossref]
9. Bastos, J. A. (2010). Forecasting bank loans loss-given-default. Journal of Banking & Finance, 34(10), 2510–2517. https://doi.org/10.1016/j.jbankfin.2010.04.011 [Google Scholar] [Crossref]
10. Brown, I., & Mues, C. (2012). An experimental comparison of classification algorithms for imbalanced credit scoring data sets. Expert Systems with Applications, 39(3), 3446–3453. https://doi.org/10.1016/j.eswa.2011.09.033 [Google Scholar] [Crossref]
11. Bussmann, N., Giudici, P., Marinelli, D., & Papenbrock, J. (2021). Explainable AI in fintech risk management. Frontiers in Artificial Intelligence, 4, Article 677857. https://doi.org/10.3389/frai.2021.677857 [Google Scholar] [Crossref]
12. Baesens, B., Van Gestel, T., Viaene, S., Stepanova, M., Suykens, J., & Vanthienen, J. (2003). Benchmarking state-of-the-art classification algorithms for credit scoring. Journal of the Operational Research Society, 54(6), 627–635. https://doi.org/10.1057/palgrave.jors.2601545 [Google Scholar] [Crossref]
13. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324 [Google Scholar] [Crossref]
14. 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). Association for Computing Machinery. https://doi.org/10.1145/2939672.2939785 [Google Scholar] [Crossref]
15. Elliott, R. J., Siu, T. K., & Fung, E. S. (2014). A double hidden Markov model for corporate credit ratings. Applied Mathematical Finance, 21(3), 203–231. https://doi.org/10.1080/1350486X.2013.875612 [Google Scholar] [Crossref]
16. Feng, G., He, J., & Polson, N. (2019). Deep learning for predicting asset returns. Frontiers of Mathematical Finance, 1(1), 1–25. https://doi.org/10.3934/fmf.2021001 [Google Scholar] [Crossref]
17. Fuster, A., Goldsmith-Pinkham, P., Ramadorai, T., & Walther, A. (2022). Predictably unequal? The effects of machine learning on credit markets. The Journal of Finance, 77(1), 5–47. https://doi.org/10.1111/jofi.13090 [Google Scholar] [Crossref]
18. Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29(5), 1189–1232. https://doi.org/10.1214/aos/1013203451 [Google Scholar] [Crossref]
19. Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning: Data mining, inference, and prediction (2nd ed.). Springer. https://doi.org/10.1007/978-0-387-84858-7 [Google Scholar] [Crossref]
20. Hauke, J., & Kossowski, T. (2011). Comparison of values of Pearson’s and Spearman’s correlation coefficients on the same sets of data. Quaestiones Geographicae, 30(2), 87–93. https://doi.org/10.2478/v10117-011-0021-1 [Google Scholar] [Crossref]
21. Jafry, Y., & Schuermann, T. (2004). Measurement, estimation and comparison of credit migration matrices. Journal of Banking & Finance, 28(11), 2603–2639. https://doi.org/10.1016/j.jbankfin.2003.10.015 [Google Scholar] [Crossref]
22. Karminsky, A., Kostrov, A., & Murzenko, V. (2016). Modeling bank credit ratings: Comparative study. Procedia Computer Science, 91, 201–210. https://doi.org/10.1016/j.procs.2016.07.049 [Google Scholar] [Crossref]
23. Kou, G., Xu, Y., Peng, Y., Shen, F., Chen, Y., Chang, K., & Kou, S. (2021). Bankruptcy prediction for SMEs using transactional data and two-stage multiobjective feature selection. Decision Support Systems, 140, Article 113429. https://doi.org/10.1016/j.dss.2020.113429 [Google Scholar] [Crossref]
24. Lessmann, S., Baesens, B., Seow, H.-V., & Thomas, L. C. (2015). Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research. European Journal of Operational Research, 247(1), 124–136. https://doi.org/10.1016/j.ejor.2015.05.030 [Google Scholar] [Crossref]
25. Löffler, G. (2004). An anatomy of rating through the cycle. Journal of Banking & Finance, 28(3), 695–720. https://doi.org/10.1016/S0378-4266(03)00103-2 [Google Scholar] [Crossref]
26. Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems (Vol. 30). Neural Information Processing Systems Foundation. [Google Scholar] [Crossref]
27. Malhotra, R., & Malhotra, D. K. (2003). Evaluating consumer loans using neural networks. Omega, 31(2), 83–96. https://doi.org/10.1016/S0305-0483(03)00016-1 [Google Scholar] [Crossref]
28. Molnar, C. (2020). Interpretable machine learning. Lulu.com. [Google Scholar] [Crossref]
29. Moody’s Investors Service. (2006). Moody’s credit rating prediction model. Moody’s Corporation. [Google Scholar] [Crossref]
30. Rijken, H. A., & Kaeck, A. (2010). The Z-metrics methodology for estimating company default risk. RiskMetrics Journal, 10(2), 45–67. [Google Scholar] [Crossref]
31. Sondhi, A. C. (1995). Evaluation of accounting differences between international and U.S. accounting standards for financial analysis. Journal of International Financial Management & Accounting, 6(2), 169–188. https://doi.org/10.1111/j.1467-646X.1995.tb00051.x [Google Scholar] [Crossref]
32. Standard & Poor’s. (2022). Corporate ratings methodology. Standard & Poor’s Global Ratings. [Google Scholar] [Crossref]
33. Tufféry, S. (2011). Data mining and statistics for decision making. Wiley. [Google Scholar] [Crossref]
34. Zhou, L., Lai, K. K., & Yen, J. (2012). Credit scoring models with AUC maximization based on weighted support vector machines. International Journal of Information Technology & Decision Making, 11(4), 749–768. https://doi.org/10.1142/S0219622012500196 [Google Scholar] [Crossref]
This work is licensed under CC BY 4.0