EU-27 bank failure prediction with C5.0 decision trees and deep learning neural networks

• Published in: Research in international business and finance Vol. 61; p. 101644
• Main Authors: Kristóf, Tamás, Virág, Miklós
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.10.2022
• Subjects: Bank failure; Classification; Credit risk modeling; Machine learning; C53; C45; G21; Classification; Machine learning; C38; Bank failure; Credit risk modeling; G17
• ISSN: 0275-5319; 1878-3384
• DOI: 10.1016/j.ribaf.2022.101644

This article provides evidence that machine learning methods are suitable for reliably predicting the failure risk of European Union-27 banks from the experiences of the past decade. It demonstrates that earnings, capital adequacy, and management capability are the strongest predictors of bank failure. Critical and relevant field research is presented in the context of economic uncertainties arising from the COVID-19 pandemic. The results suggest that the developed models possess high predictive power, with the C5.0 decision tree model providing the best performance. The findings have policy implications for bank supervisory authorities, bank executives, risk management professionals, and policymakers working in finance. The models can be used to recognize bank weaknesses in time to take appropriate mitigating actions. [Display omitted] •Failure risk of EU-27 banks can be reliably modelled by use of machine learning techniques.•Earnings, capital adequacy, and management capability are the strongest predictors of bank failure in the EU-27 area.•Decision trees are beneficial to create categorical variables to enhance model performance.•The C5.0 decision tree model indicates the best result, followed by the deep learning neural network model, but the logistic regression model also performs fairly efficiently.