Predicting Financial Distress with Machine Learning and Explainable Artificial Intelligence: A Study on BIST

Abstract

Predicting financial distress is vital for business survival in dynamic environments. This prediction is realized with the help of models built on financial ratios. Classical models are frequently used to predict financial distress. However, models based on machine learning (ML) algorithms offer new perspectives in this field. This study aims to classify financial distress using ML algorithms. In this study, 39 financial ratios were obtained from the financial statements of 198 enterprises operating in Borsa Istanbul (BIST) between 2015 and 2020. The study was evaluated using three different scenarios. First, all ratios were analyzed using ML algorithms. Second, financial ratios selected via F-regression were used and these ratios were classified using ML algorithms. Third, the stacking ML models were classified into all and selected ratios. All models were tested with a 10-fold cross-validation. According to the experimental results, the CatBoost algorithm obtained the highest average accuracy, with 0.967 in the second scenario. In general, the Boosting-based algorithms showed higher performance than the other algorithms. In addition, the results obtained with the CatBoost algorithm were evaluated by the SHapley Additive exPlanations analysis to explain the importance of financial ratios. SHAP analysis applied to the CatBoost algorithm revealed that the equity-to-asset-ratio (Feature 4) and debt ratio (Feature 3) were the most effective variables in predicting financial distress. The findings underscore the importance of capital structure in assessing financial distress.

Keywords

• Financial Distress
• Financial Ratio
• Borsa Istanbul
• Machine Learning
• Explainable Artificial Intelligence

References

1. Abdullah, D. A. & AL-Anber, N. J. (2021). A Data Mining Approach To Detection Financial Distress In Iraqi Companies. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12 (14), 2107-2119. google scholar
2. Aksoy, B. & Boztosun, D. (2021). Comparison of classification performance of machine learning methods in prediction financial failure: Evidence from Borsa İstanbul. Hitit Sosyal Bilimler Dergisi, 14 (1), 56-86. https://doi.org/10.17218/hititsbd.880658. google scholar
3. Altman, E. I. (1968). Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. The journal of finance, 23 (4), 589-609. google scholar
4. 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. http://dx.doi.org/10.1111/jifm.12053. google scholar
5. Aydin, N., Sahin, N., Deveci, M. & Pamucar, D. (2022). Prediction of financial distress of companies with artificial neural networks and decision trees models. Machine Learning with Applications, 10, 100432. https://doi.org/10.1016/j.mlwa.2022.100432 . google scholar
6. Beaver, W. H. (1966). Financial ratios as predictors of failure.Journal of accounting research ,71-111 . google scholar
7. Breiman, L.(200l). Random forests.Machine learning ,45 ,5-32 . google scholar
8. Bumin,M.& Ozcalici,M.(2023). Predicting the direction of financial dollarization movement with genetic algorithm and machine learning algorithms: The case of Turkey.Expert Systems with Applications ,2l3 ,l l93Ol .https://doi.org/ lO.lOl6/j.eswa.zOZz.ll93Ol . google scholar

9. Büyükarıkan, B. & Büyükarıkan, U. (2018). Kimya Sektörü İşletmelerinde Finansal Başarisizliğin Tahmini. Hacettepe Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 36 (3), 29-50. https://doi.org/10.17065/huniibf.290670. google scholar
10. Chen, T. & Guestrin, C. (2016) of Conference. Xgboost: A scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, 785-794. google scholar
11. Cortes, C. & Vapnik, V. (1995). Support-vector networks. Machine learning, 20, 273-297. https://doi.org/10.1007/BF00994018. google scholar
12. Cover, T. & Hart, P. (1967). Nearest neighbor pattern classification.IEEE transactions on Information Theory, 13 (1), 21-27.https://doi.org/10.1109/TIT.1967.1053964 . google scholar
13. Cox, D. R.(1958). The regression analysis of binary sequences.Journal of the Royal Statistical Society Series B: Statistical Methodology ,20 (2), 215-232 . google scholar
14. Dimitras, A. I., Zanakis, S. H. & Zopounidis, C. (1996). A survey of business failures with an emphasis on prediction methods and industrial applications. European journal of operational research, 90 (3), 487-513. https://doi.org/10.1016/0377-2217(95)00070-4. google scholar
15. Dizgil, E. (2018). BIST Ticaret Endeksinde yer alan şirketlerin Springate finansal başarısızlık modeli ile incelenmesi. Bilecik Şeyh Edebali Üniversitesi Sosyal Bilimler Dergisi, 3 (2), 248-267. google scholar
16. Elhoseny, M., Metawa, N., Sztano, G. & El-Hasnony, I. M. (2025). Deep learning-based model for financial distress prediction. Annals of operations research, 345 (2), 885-907. google scholar
17. Engin, U. & Durer, S. (2023). Financial distress prediction from time series data using xgboost: Bist100 of borsa istanbul. Doğuş Üniversitesi Dergisi, 24 (2), 589-604. google scholar
18. Fisher, R. A. (1936). The use of multiple measurements in taxonomic problems.Annals of eugenics ,7 (2), 179-188 . google scholar
19. Freund, Y. & Schapire, R. E. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of computer and system sciences, 55 (1), 119-139. https://doi.org/10.1006/jcss.1997.1504. google scholar
20. Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of statistics, 1189-1232. google scholar
21. Fulmer, J. G., Moon, J. E., Gavin, T. A. & Erwin, M. (1984). A bankruptcy classification model for small firms. Journal of commercial bank lending, 66 (11), 25-37. google scholar
22. Geurts, P., Ernst, D. & Wehenkel, L. (2006). Extremely randomized trees. Machine learning, 63, 3-42. google scholar
23. Ghisellini, P. & Ulgiati, S. (2020). Circular economy transition in Italy. Achievements, perspectives and constraints.Journal of cleaner production ,243 ,118360 . google scholar
24. Gregova, E., Valaskova, K., Adamko, P., Tumpach, M. & Jaros, J. (2020). Predicting financial distress of slovak enterprises: Comparison of selected traditional and learning algorithms methods. Sustainability, 12 (10), 3954. https://doi.org/10.3390/su12103954. google scholar
25. Hafiz, A., Lukumon, O., Muhammad, B., Olugbenga, A., Hakeem, O. & Saheed, A. (2015) of Conference. Bankruptcy prediction of construction businesses: towards a big data analytics approach. 2015 IEEE first international conference on big data computing service and applications, 347-352. https://doi.org/10.1109/BigDataService.2015.30. google scholar
26. Han, J., Kamber, M. & Pei, J. (2012). Data Mining: Concepts and Techniques (Vol. 5). Massachusetts: Morgan Kaufmann. google scholar
27. Huang, C., Dai, C. & Guo, M. (2015). A hybrid approach using two-level DEA for financial failure prediction and integrated SE-DEA and GCA for indicators selection.Applied Mathematics and Computation ,251 ,431-441 . https://doi.org/10.1016/j.amc.2014.11.077 . google scholar
28. Huang, Y.-P. & Yen, M.-F. (2019). A new perspective of performance comparison among machine learning algorithms for financial distress prediction.Applied Soft Computing ,83 ,lO5663 . https://doi.org/ lO.lOl6/j.asoc.zOl9.lO5663 . google scholar
29. Jawabreh, O. A., Al Rawashdeh, F. & Senjelawi, O. (2017). Using Altman's Z-Score model to predict the financial failure of hospitality companies-case of Jordan. International Journal of Information, Business and Management, 9 (2), 141. google scholar
30. Jiang, C., Zhou, Y. & Chen, B. (2023). Mining semantic features in patent text for financial distress prediction. Technological Forecasting and Social Change, 190, 122450. https://doi.org/10.1016/j.techfore.2023.122450. google scholar
31. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q. & Liu, T.-Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30. google scholar
32. Laitinen, E. K. & Laitinen, T. (2000). Bankruptcy prediction: Application of the Taylor's expansion in logistic regression.International review of financial analysis ,9 (4), 327-349 . https://doi.org/10.1016/S1057-5219(00)00039-9 . google scholar
33. Malakauskas, A. & Lakštutienė, A. (2021). Financial distress prediction for small and medium enterprises using machine learning techniques.Engineering Economics ,32 (1), 4-14 . https://doi.org/10.5755/j01.ee.32.1.27382 . google scholar
34. Medetoğlu, B. & Tutar, S. (2023). Springate S ve Fulmer H skor modelleri ile finansal başarisizlik tespiti: borsa İstanbul tekstil, giyim eşyasi ve deri sektörü üzerine bir uygulama. Doğuş Üniversitesi Dergisi, 24 (1), 307-319. google scholar
35. Ohlson, J. A. (1980). Financial ratios and the probabilistic prediction of bankruptcy. Journal of accounting research, 109-131. https://doi.org/10.2307/2490395. google scholar
36. Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V. & Gulin, A. (2018). CatBoost: unbiased boosting with categorical features. Advances in neural information processing systems, 31. google scholar
37. Qian, H., Wang, B., Yuan, M., Gao, S. & Song, Y. (2022). Financial distress prediction using a corrected feature selection measure and gradient boosted decision tree. Expert Systems with Applications, 190, 116202. https://doi.org/10.1016/j.eswa.2021.116202. google scholar
38. Rumelhart, D. E., Hinton, G. E. & Williams, R. J. (1986). Learning representations by back-propagating errors.nature ,323 (6088), 533-536 . google scholar
39. Saha, P. (2024). Comprehensive Analysis of Altman’s Z Score, Zmijewski X Score, Springate S-Score and Grover G-Score Model for Predicting Financial Health of Listed Non-Bank Financial Institutions (NBFIs) of Bangladesh. Open Journal of Business and Management, 12, 3342-3365. google scholar
40. Sánchez-Almeyda, C., González-Bueno, J., Koval, V., Reyes-Maldonado, N., Kryshtal, H. & Zharikova, O. (2025). Predicting financial distress in the food production sector: a dual-model approach using Z-score and O-score methods. Discover Sustainability, 6 (1), 731. google scholar
41. Sankhwar, S., Gupta, D., Ramya, K., Rani, S. S., Shankar, K. & Lakshmanaprabu, S. (2020). Improved grey wolf optimization-based feature subset selection with fuzzy neural classifier for financial crisis prediction. Soft Computing, 24 (1), 101-110. google scholar
42. Selimefendigil, S. (2023). Predicting financial distress using supervised machine learning algorithms: an application on borsa istanbul. Journal of Economics Finance and Accounting, 10 (4), 217-223. google scholar
43. Sethi, P., Singh, A. & Gupta, V. (2025). Predicting Financial Distress Using Machine Learning Techniques. Asia-Pacific Financial Markets, 1-23. google scholar
44. Soydaş, S. & Çam, H. (2024). Predicting Financial Failure in Companies by Employing Machine Learning Methods. International Journal of Social Science Research and Review, 7, 111-125. google scholar
45. Springate, G. L. (1978), Predicting the possibility of failure in a Canadian firm: A discriminant analysis, Simon Fraser University. google scholar
46. Sun, J., Li, H., Huang, Q.-H. & He, K.-Y. (2014). Predicting financial distress and corporate failure: A review from the state-of-the-art definitions, modeling, sampling, and featuring approaches. Knowledge-Based Systems, 57, 41-56. https://doi.org/10.1016/j.knosys.2013.12.006. google scholar
47. Sun, J., Fujita, H., Zheng, Y. & Ai, W. (2021). Multi-class financial distress prediction based on support vector machines integrated with the decomposition and fusion methods. Information Sciences, 559, 153-170. https://doi.org/10.1016/j.ins.2021.01.059. google scholar
48. Tran, K. L., Le, H. A., Nguyen, T. H. & Nguyen, D. T. (2022). Explainable Machine Learning for Financial Distress Prediction: Evidence from Vietnam.Data ,7 (11), 160 . https://doi.org/10 .3390/data7l lO l6O . google scholar
49. Van Gestel, T., Baesens, B., Suykens, J. A., Van den Poel, D., Baestaens, D.-E. & Willekens, M. (2006). Bayesian kernel based classification for financial distress detection. European journal of operational research, 172 (3), 979-1003. https://doi.org/10.1016/j.ejor.2004.11.009. google scholar
50. Wang, G., Chen, G. & Chu, Y. (2018). A new random subspace method incorporating sentiment and textual information for financial distress prediction. Electronic Commerce Research and Applications, 29, 30-49. https://doi.org/10.1016/j.elerap.2018.03.004. google scholar
51. Yakut, E. & Elmas, B. (2013). Estimating financial failure of enterprises with data mining and discriminant analysis.Afyon Kocatepe University İİBF Journal ,15 (1), 237-254 . google scholar
52. Yıldırım, M. Ç. & Özekenci, S. Y. (2025). Finansal başarısızlık tahmin modellerinin karşılaştırılması: BİST gıda ve içecek sektöründe bir uygulama.Üçüncü Sektör Sosyal Ekonomi Dergisi ,60 (1), 982-1004 . google scholar
53. Zhang, R., Zhang, Z., Wang, D. & Du, M. (2022). Financial Distress Prediction with a Novel Diversity-Considered GA-MLP Ensemble Algorithm.Neural Processing Letters ,54, 1175–1194 . https://doi.org/10 .3390/data7l lO l6O . google scholar
54. Zhao, S., Xu, K., Wang, Z., Liang, C., Lu, W. & Chen, B. (2022). Financial distress prediction by combining sentiment tone features. Economic Modelling, 106, 105709. https://doi.org/10.1016/j.econmod.2021.105709. google scholar
55. Zhong, J. & Wang, Z. (2022). Artificial intelligence techniques for financial distress prediction. AIMS Mathematics, 7 (12), 20891-20908. google scholar