Personal bankruptcy prediction using machine learning techniques

Brygała, Magdalena; Korol, Tomasz

doi:10.18559/ebr.2024.2.1149

Abstract

It has become crucial to have an early prediction model that provides accurate assurance for users about the financial situation of consumers. Recent studies have focused on predicting corporate bankruptcies and credit defaults, not personal bankruptcies. Due to this situation, the present study fills the literature gap by comparing different machine learning algorithms to predict personal bankruptcy. The main objective of the study is to examine the usefulness of machine learning models such as SVM, random forest, AdaBoost, XGBoost, LightGBM, and CatBoost in forecasting personal bankruptcy. The study relies on two samples of households (learning and testing) from the Survey of Consumer Finances, which was conducted in the United States. Among the models estimated, LightGBM, CatBoost, and XGBoost showed the highest effectiveness. The most important variables used in the models are income, refusal to grant credit, delays in the repayment of liabilities, the revolving debt ratio, and the housing debt ratio.

References

Al Daoud, E. (2019). Comparison between XGBoost, LightGBM and CatBoost using a home credit dataset. International Journal of Computer and Information Engineering, 13(1), 6–10.
Search in Google Scholar Back to article
Alam, N., Gao, J., & Jones, S. (2021). Corporate failure prediction: An evaluation of deep learning vs discrete hazard models. Journal of International Financial Markets, Institutions and Money, 75, 101455. https://doi.org/10.1016/j.intfin.2021.101455
Search in Google Scholar Back to article
Alfaro, E., García, N., Gámez, M., & Elizondo, D. (2008). Bankruptcy forecasting: An empirical comparison of AdaBoost and neural networks. Decision Support Systems, 45(1), 110–122. https://doi.org/10.1016/j.dss.2007.12.002
Search in Google Scholar Back to article
Altman, E. I., & Kuehne, B. J. (2016). Credit markets and bubbles: Is the benign credit cycle over? Economics and Business Review, 2(3), 20–31. https://doi.org/10.18559/ebr.2016.3.3
Search in Google Scholar Back to article
Barboza, F., Basso, L. F. C., & Kimura, H. (2021). New metrics and approaches for predicting bankruptcy. Communications in Statistics-Simulation and Computation, 52(6), 2615–2632. https://doi.org/10.1080/03610918.2021.1910837
Search in Google Scholar Back to article
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
Search in Google Scholar Back to article
Berlemann, M., & Salland, J. (2016). The Joneses’ income and debt market participation: Empirical evidence from bank account data. Economics Letters, 142, 6–9. https://doi.org/10.1016/j.econlet.2016.02.030
Search in Google Scholar Back to article
Bragoli, D., Ferretti, C., Ganugi, P., Marseguerra, G., Mezzogori, D., & Zammori, F. (2022). Machine-learning models for bankruptcy prediction: do industrial variables matter? Spatial Economic Analysis, 17(2), 156–177. https://doi.org/10.1080/17421772.2021.1977377
Search in Google Scholar Back to article
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
Search in Google Scholar Back to article
Brotcke, L. (2022). Time to assess bias in machine learning models for credit decisions. Journal of Risk and Financial Management, 15(4), 165. https://doi.org/10.3390/jrfm15040165
Search in Google Scholar Back to article
Brygała, M. (2022). Consumer bankruptcy prediction using balanced and imbalanced data. Risks, 10(2), 24. https://doi.org/10.3390/risks10020024
Search in Google Scholar Back to article
Bussmann, N., Giudici, P., Marinelli, D., & Papenbrock, J. (2020). Explainable AI in fintech risk management. Frontiers in Artificial Intelligence, 3, 26. https://doi.org/10.3389/frai.2020.00026
Search in Google Scholar Back to article
Carmona, P., Dwekat, A., & Mardawi, Z. (2022). No more black boxes! Explaining the predictions of a machine learning XGBoost classifier algorithm in business failure. Research in International Business and Finance, 61, 101649. https://doi.org/10.1016/j.ribaf.2022.101649
Search in Google Scholar Back to article
Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp. 785–794. https://doi.org/10.1145/2939672.2939785
Search in Google Scholar Back to article
CFPB (Consumer Financial Protection Bureau). (2022). Is a lender allowed to consider my age or where my income comes from when deciding whether to give me a loan? https://www.consumerfinance.gov/ask-cfpb/is-a-lender-allowed-to-consider-my-age-or-where-my-income-comes-from-when-deciding-whether-to-give-me-a-loan-en-1181/
Search in Google Scholar Back to article
Coşer, A., Maer-matei, M. M., & Albu, C. (2019). Predictive models for loan default risk assessment. Economic Computation & Economic Cybernetics Studies & Research, 53(2). https://doi.org/10.24818/18423264/53.2.19.09
Search in Google Scholar Back to article
de Castro Vieira, J. R., Barboza, F., Sobreiro, V. A., & Kimura, H. (2019). Machine learning models for credit analysis improvements: Predicting low-income families’ default. Applied Soft Computing, 83, 105640. https://doi.org/10.1016/j.asoc.2019.105640
Search in Google Scholar Back to article
Dorogush, A. V., Ershov, V., & Gulin, A. (2018). CatBoost: Gradient boosting with categorical features support. https://doi.org/10.48550/arXiv.1810.11363
Search in Google Scholar Back to article
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
Search in Google Scholar Back to article
Garcia, J. (2022). Bankruptcy prediction using synthetic sampling. Machine Learning with Applications, 9, 100343. https://doi.org/10.1016/j.mlwa.2022.100343
Search in Google Scholar Back to article
Georgarakos, D., Haliassos, M., & Pasini, G. (2014). Household debt and social interactions. The Review of Financial Studies, 27(5), 1404–1433. https://doi.org/10.1093/rfs/hhu014
Search in Google Scholar Back to article
Gramegna, A., & Giudici, P. (2021). SHAP and LIME: An evaluation of discriminative power in credit risk. Frontiers in Artificial Intelligence, 4, 752558. https://doi.org/10.3389/frai.2021.752558
Search in Google Scholar Back to article
Halim, Z., Shuhidan, S. M., & Sanusi, Z. M. (2021). Corporation financial distress prediction with deep learning: Analysis of public listed companies in Malaysia. Business Process Management Journal, 274), 1163–1178. https://doi.org/10.1108/bpmj-062020-0273
Search in Google Scholar Back to article
Hancock, J. T., & Khoshgoftaar, T. M. (2020). CatBoost for big data: An interdisciplinary review. Journal of Big Data, 7(1), 94. https://doi.org/10.1186/s40537-020-00369-8
Search in Google Scholar Back to article
Heo, J., & Yang, J. Y. (2014). AdaBoost based bankruptcy forecasting of Korean construction companies. Applied Soft Computing, 24, 494–499. https://doi.org/10.1016/j.asoc.2014.08.009
Search in Google Scholar Back to article
Jabeur, S. B., Gharib, C., Mefteh-Wali, S., & Arfi, W. B. (2021). CatBoost model and artificial intelligence techniques for corporate failure prediction. Technological Forecasting and Social Change, 166, 120658. https://doi.org/10.1016/j.techfore.2021.120658
Search in Google Scholar Back to article
Jabeur, S. B., Mefteh-Wali, S., & Viviani, J. L. (2021). Forecasting gold price with the XGBoost algorithm and SHAP interaction values. Annals of Operations Research, 334, 679–699. https://doi.org/10.1007/s10479-021-04187-w
Search in Google Scholar Back to article
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.
Search in Google Scholar Back to article
Khare, N., & Sait, S. Y. (2018). Credit card fraud detection using machine learning models and collating machine learning models. International Journal of Pure and Applied Mathematics, 118(20), 825–838.
Search in Google Scholar Back to article
Korol, T. (2021). Examining statistical methods in forecasting financial energy of households in Poland and Taiwan. Energies, 14(7), 1821. https://doi.org/10.3390/en14071821
Search in Google Scholar Back to article
Korol, T., & Fotiadis, A. K. (2022). Implementing artificial intelligence in forecasting the risk of personal bankruptcies in Poland and Taiwan. Oeconomia Copernicana, 13(2), 407. https://doi.org/10.24136/oc.2022.013
Search in Google Scholar Back to article
Kovacova, M., Kliestik, T., Valaskova, K., Durana, P., & Juhaszova, Z. (2019). Systematic review of variables applied in bankruptcy prediction models of Visegrad group countries. Oeconomia Copernicana, 10(4), 743–772. https://doi.org/10.24136/oc.2019.034
Search in Google Scholar Back to article
Kovacova, M., & Kliestikova, J. (2017). Modelling bankruptcy prediction models in Slovak companies. SHS Web of Conferences, vol. 39, p. 01013. EDP Sciences. https://doi.org/10.1051/shsconf/20173901013
Search in Google Scholar Back to article
Le, T., Lee, M. Y., Park, J. R., & Baik, S. W. (2018). Oversampling techniques for bankruptcy prediction: Novel features from a transaction dataset. Symmetry, 10(4), 79. https://doi.org/10.3390/sym10040079
Search in Google Scholar Back to article
Letza, S. R., Kalupa, Ł., & Kowalski, T. (2003). Predicting corporate failure: How useful are multi discriminant analysis models? Economics and Business Review, 3(2), 5–11. https://doi.org/10.18559/ebr.2003.2.494
Search in Google Scholar Back to article
Liang, D., Lu, C. C., Tsai, C. F., & Shih, G. A. (2016). Financial ratios and corporate governance indicators in bankruptcy prediction: A comprehensive study. European Journal of Operational Research, 252(2), 561–572. https://doi.org/10.1016/j.ejor.2016.01.012
Search in Google Scholar Back to article
Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30.
Search in Google Scholar Back to article
Machado, M. R., & Karray, S. (2022). Assessing credit risk of commercial customers using hybrid machine learning algorithms. Expert Systems with Applications, 200, 116889. https://doi.org/10.1016/j.eswa.2022.116889
Search in Google Scholar Back to article
Mangalathu, S., Hwang, S. H., & Jeon, J. S. (2020). Failure mode and effects analysis of RC members based on machine-learning-based SHapley Additive exPlanations (SHAP) approach. Engineering Structures, 219, 110927. https://doi.org/10.1016/j.engstruct.2020.110927
Search in Google Scholar Back to article
Mihalovič, M. (2016). Performance comparison of multiple discriminant analysis and logit models in bankruptcy prediction. Economics & Sociology, 9(4). https://doi.org/10.14254/2071-789x.2016/9-4/6
Search in Google Scholar Back to article
Mo, H., Sun, H., Liu, J., & Wei, S. (2019). Developing window behavior models for residential buildings using XGBoost algorithm. Energy and Buildings, 205, 109564. https://doi.org/10.1016/j.enbuild.2019.109564
Search in Google Scholar Back to article
Papík, M., & Papíková, L. (2023). Impacts of crisis on SME bankruptcy prediction models’ performance. Expert Systems with Applications, 214, 119072. https:/doi.org/10.1016/j.eswa.2022.119072
Search in Google Scholar Back to article
Papík, M., Papíková, L., Kajanová, J., & Bečka, M. (2023). CatBoost: The case of bankruptcy prediction. International Conference on Business and Technology, pp. 3–17. Springer.
Search in Google Scholar Back to article
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.
Search in Google Scholar Back to article
Saarela, M., & Jauhiainen, S. (2021). Comparison of feature importance measures as explanations for classification models. SN Applied Sciences, 3, 272. https://doi.org/10.1007/s42452-021-04148-9
Search in Google Scholar Back to article
Sahiq, A. N. M., Ismail, S., Nor, S. H. S., Ul-Saufie, A. Z., & Yaacob, W. F. W. (2022, September). Application of logistic regression model on imbalanced data in personal bankruptcy prediction. 2022 3rd International Conference on Artificial Intelligence and Data Sciences (AiDAS) (pp. 120–125). IEEE. https://doi.org/10.1109/aidas56890.2022.9918779
Search in Google Scholar Back to article
Schonlau, M., & Zou, R. Y. (2020). The random forest algorithm for statistical learning. The Stata Journal, 20(1), 3–29. https://doi.org/10.1177/1536867x20909688
Search in Google Scholar Back to article
Shi, S., Tse, R., Luo, W., D’Addona, S., & Pau, G. (2022). Machine learning-driven credit risk: A systemic review. Neural Computing and Applications, 34(17), 14327–14339. https://doi.org/10.1007/s00521-022-07472-2
Search in Google Scholar Back to article
Son, H., Hyun, C., Phan, D., & Hwang, H. J. (2019). Data analytic approach for bankruptcy prediction. Expert Systems with Applications, 138, 112816. https://doi.org/10.1016/j.eswa.2019.07.033
Search in Google Scholar Back to article
Syam, N., & Sharma, A. (2018). Waiting for a sales renaissance in the fourth industrial revolution: Machine learning and artificial intelligence in sales research and practice. Industrial Marketing Management, 69, 135–146. https://doi.org/10.1016/j.indmarman.2017.12.019
Search in Google Scholar Back to article
Syed Nor, S. H., Ismail, S., & Yap, B. W. (2019). Personal bankruptcy prediction using decision tree model. Journal of Economics, Finance and Administrative Science, 24(47), 157–170. https://doi.org/10.1108/jefas-08-2018-0076
Search in Google Scholar Back to article
Wang, D. N., Li, L., & Zhao, D. (2022). Corporate finance risk prediction based on LightGBM. Information Sciences, 602, 259–268. https://doi.org/10.1016/j.ins.2022.04.058
Search in Google Scholar Back to article
Wu, D. J., Feng, T., Naehrig, M., & Lauter, K. E. (2016). Privately evaluating decision trees and random forests. Proceedings on Privacy Enhancing Technologies, (4), 335–355. https://doi.org/10.1515/popets-2016-0043
Search in Google Scholar Back to article
Yen, S. J., & Lee, Y. S. (2009). Cluster-based under-sampling approaches for imbalanced data distributions. Expert Systems with Applications, 36(3), 5718–5727. https://doi.org/10.1016/j.eswa.2008.06.108
Search in Google Scholar Back to article
Zelenkov, Y., & Volodarskiy, N. (2021). Bankruptcy prediction on the base of the unbalanced data using multi-objective selection of classifiers. Expert Systems with Applications, 185, 115559. https://doi.org/10.1016/j.eswa.2021.115559
Search in Google Scholar Back to article
Zhang, L., Wang, J., & Liu, Z. (2023). What should lenders be more concerned about? Developing a profit-driven loan default prediction model. Expert Systems with Applications, 213, 118938. https://doi.org/10.1016/j.eswa.2022.118938
Search in Google Scholar Back to article

Personal bankruptcy prediction using machine learning techniques

Abstract

Paradigm

My account