Skip to main content
Top

Hint

Swipe to navigate through the articles of this issue

07-09-2023 | Original Research

Bankruptcy prediction using machine learning and Shapley additive explanations

Authors: Hoang Hiep Nguyen, Jean-Laurent Viviani, Sami Ben Jabeur

Published in: Review of Quantitative Finance and Accounting

Log in

Abstract

Recently, ensemble-based machine learning models have been widely used and have demonstrated their efficiency in bankruptcy prediction. However, these algorithms are black box models and people cannot understand why they make their forecasts. This explains why interpretability methods in machine learning attract attention from many artificial intelligence researchers. In this paper, we evaluate the prediction performance of Random Forest, LightGBM, XGBoost, and NGBoost (Natural Gradient Boosting for probabilistic prediction) for French firms from different industries with the horizon of 1–5 years. We then use Shapley Additive Explanations (SHAP), a model-agnostic method to explain XGBoost, one of the best models for our data. SHAP can show how each feature impacts the output from XGBoost. Furthermore, single prediction can also be explained, thus allowing black box models to be used in credit risk management.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Appendix
Available only for authorised users
Literature
go back to reference Alaka HA, Oyedele LO, Owolabi HA et al (2018) Systematic review of bankruptcy prediction models: towards a framework for tool selection. Expert Syst Appl 94:164–184 CrossRef Alaka HA, Oyedele LO, Owolabi HA et al (2018) Systematic review of bankruptcy prediction models: towards a framework for tool selection. Expert Syst Appl 94:164–184 CrossRef
go back to reference Altman EI (1968) Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. J Finance 23:589–609 CrossRef Altman EI (1968) Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. J Finance 23:589–609 CrossRef
go back to reference Altman EI, Haldeman RG, Narayanan P (1977) ZETATM analysis A new model to identify bankruptcy risk of corporations. J Bank Finance 1:29–54 CrossRef Altman EI, Haldeman RG, Narayanan P (1977) ZETATM analysis A new model to identify bankruptcy risk of corporations. J Bank Finance 1:29–54 CrossRef
go back to reference Bardos M (1995) Détection précoce des défaillances d’entreprises à partir des documents comptables. Bulletin De La Banque De France 3:57–71 Bardos M (1995) Détection précoce des défaillances d’entreprises à partir des documents comptables. Bulletin De La Banque De France 3:57–71
go back to reference Bellovary JL, Giacomino DE, Akers MD (2007) A review of bankruptcy prediction studies: 1930 to present. J Financ Educ 33:1–42 Bellovary JL, Giacomino DE, Akers MD (2007) A review of bankruptcy prediction studies: 1930 to present. J Financ Educ 33:1–42
go back to reference Ben Jabeur S, Stef N, Carmona P (2023) Bankruptcy prediction using the XGBoost algorithm and variable importance feature engineering. Comput Econ 61:715–741 CrossRef Ben Jabeur S, Stef N, Carmona P (2023) Bankruptcy prediction using the XGBoost algorithm and variable importance feature engineering. Comput Econ 61:715–741 CrossRef
go back to reference Charalambous C, Martzoukos SH, Taoushianis Z (2022) Estimating corporate bankruptcy forecasting models by maximizing discriminatory power. Rev Quant Financ Acc 58:297–328 CrossRef Charalambous C, Martzoukos SH, Taoushianis Z (2022) Estimating corporate bankruptcy forecasting models by maximizing discriminatory power. Rev Quant Financ Acc 58:297–328 CrossRef
go back to reference Charalambous C, Martzoukos S, Taoushianis Z (2023) A neuro-structural framework for bankruptcy prediction. Quant Finance ( forthcoming) Charalambous C, Martzoukos S, Taoushianis Z (2023) A neuro-structural framework for bankruptcy prediction. Quant Finance ( forthcoming)
go back to reference Chen T-K, Liao H-H, Chen G-D et al (2023) Bankruptcy prediction using machine learning models with the text-based communicative value of annual reports. Expert Syst Appl 233:120714 CrossRef Chen T-K, Liao H-H, Chen G-D et al (2023) Bankruptcy prediction using machine learning models with the text-based communicative value of annual reports. Expert Syst Appl 233:120714 CrossRef
go back to reference Dikshit A, Pradhan B (2021) Interpretable and explainable AI (XAI) model for spatial drought prediction. Sci Total Environ 801:149797 CrossRef Dikshit A, Pradhan B (2021) Interpretable and explainable AI (XAI) model for spatial drought prediction. Sci Total Environ 801:149797 CrossRef
go back to reference du Jardin P (2016) A two-stage classification technique for bankruptcy prediction. Eur J Oper Res 254:236–252 CrossRef du Jardin P (2016) A two-stage classification technique for bankruptcy prediction. Eur J Oper Res 254:236–252 CrossRef
go back to reference Duan T, Anand A, Ding DY et al (2020) Ngboost: Natural gradient boosting for probabilistic prediction. In: International conference on machine learning. PMLR, pp 2690–2700 Duan T, Anand A, Ding DY et al (2020) Ngboost: Natural gradient boosting for probabilistic prediction. In: International conference on machine learning. PMLR, pp 2690–2700
go back to reference Jabeur SB, Serret V (2023) Bankruptcy prediction using fuzzy convolutional neural networks. Res Int Bus Financ 64:101844 CrossRef Jabeur SB, Serret V (2023) Bankruptcy prediction using fuzzy convolutional neural networks. Res Int Bus Financ 64:101844 CrossRef
go back to reference Jones S, Johnstone D, Wilson R (2017) Predicting corporate bankruptcy: An evaluation of alternative statistical frameworks. J Bus Financ Acc 44:3–34 CrossRef Jones S, Johnstone D, Wilson R (2017) Predicting corporate bankruptcy: An evaluation of alternative statistical frameworks. J Bus Financ Acc 44:3–34 CrossRef
go back to reference Ke G, Meng Q, Finley T et al (2017) LightGBM: A highly efficient gradient boosting decision tree. In: Advances in neural information processing systems, pp 3146–3154 Ke G, Meng Q, Finley T et al (2017) LightGBM: A highly efficient gradient boosting decision tree. In: Advances in neural information processing systems, pp 3146–3154
go back to reference Lundberg SM, Lee S-I (2017) A unified approach to interpreting model predictions. In: Advances in neural information processing systems vol 30 Lundberg SM, Lee S-I (2017) A unified approach to interpreting model predictions. In: Advances in neural information processing systems vol 30
go back to reference Moen PA (2020) Bankruptcy prediction for Norwegian enterprises using interpretable machine learning models with a novel timeseries problem formulation. Master’s thesis, NTNU Moen PA (2020) Bankruptcy prediction for Norwegian enterprises using interpretable machine learning models with a novel timeseries problem formulation. Master’s thesis, NTNU
go back to reference Molnar C, König G, Herbinger J et al (2022) General pitfalls of model-agnostic interpretation methods for machine learning models. In: International workshop on extending explainable AI beyond deep models and classifiers. Springer, pp 39–68 Molnar C, König G, Herbinger J et al (2022) General pitfalls of model-agnostic interpretation methods for machine learning models. In: International workshop on extending explainable AI beyond deep models and classifiers. Springer, pp 39–68
go back to reference Odom MD, Sharda R (1990) A neural network model for bankruptcy prediction. In: 1990 IJCNN international joint conference on neural networks. IEEE, San Diego, CA, USA, vol 2, pp 163–168 Odom MD, Sharda R (1990) A neural network model for bankruptcy prediction. In: 1990 IJCNN international joint conference on neural networks. IEEE, San Diego, CA, USA, vol 2, pp 163–168
go back to reference Perboli G, Arabnezhad E (2021) A machine learning-based DSS for mid and long-term company crisis prediction. Expert Syst Appl 174:114758 CrossRef Perboli G, Arabnezhad E (2021) A machine learning-based DSS for mid and long-term company crisis prediction. Expert Syst Appl 174:114758 CrossRef
go back to reference Porter ME (2008) Competitive advantage: creating and sustaining superior performance. Simon and Schuster, New York Porter ME (2008) Competitive advantage: creating and sustaining superior performance. Simon and Schuster, New York
go back to reference Sigrist F, Leuenberger N (2023) Machine learning for corporate default risk: multi-period prediction, frailty correlation, loan portfolios, and tail probabilities. Eur J Oper Res 305:1390–1406 CrossRef Sigrist F, Leuenberger N (2023) Machine learning for corporate default risk: multi-period prediction, frailty correlation, loan portfolios, and tail probabilities. Eur J Oper Res 305:1390–1406 CrossRef
go back to reference Staňková M (2023) Threshold moving approach with logit models for bankruptcy prediction. Comput Econ 61:1251–1272 CrossRef Staňková M (2023) Threshold moving approach with logit models for bankruptcy prediction. Comput Econ 61:1251–1272 CrossRef
go back to reference Veganzones D, Séverin E (2018) An investigation of bankruptcy prediction in imbalanced datasets. Decis Support Syst 112:111–124 CrossRef Veganzones D, Séverin E (2018) An investigation of bankruptcy prediction in imbalanced datasets. Decis Support Syst 112:111–124 CrossRef
go back to reference Zhang K, Xu P, Zhang J (2020) Explainable AI in deep reinforcement learning models: A shap method applied in power system emergency control. In: 2020 IEEE 4th conference on energy internet and energy system integration (EI2). IEEE, pp 711–716 Zhang K, Xu P, Zhang J (2020) Explainable AI in deep reinforcement learning models: A shap method applied in power system emergency control. In: 2020 IEEE 4th conference on energy internet and energy system integration (EI2). IEEE, pp 711–716
go back to reference Zmijewski ME (1984) Methodological issues related to the estimation of financial distress prediction models. J Account Res 22:59–82 CrossRef Zmijewski ME (1984) Methodological issues related to the estimation of financial distress prediction models. J Account Res 22:59–82 CrossRef
Metadata
Title
Bankruptcy prediction using machine learning and Shapley additive explanations
Authors
Hoang Hiep Nguyen
Jean-Laurent Viviani
Sami Ben Jabeur
Publication date
07-09-2023
Publisher
Springer US
Published in
Review of Quantitative Finance and Accounting
Print ISSN: 0924-865X
Electronic ISSN: 1573-7179
DOI
https://doi.org/10.1007/s11156-023-01192-x