CORPORATE LEVERAGE AND FINANCIAL DISTRESS PREDICTION USING ENSEMBLE LEARNING MODELS
Keywords:
Corporate Leverage, Financial Distress, Ensemble Learning, XGBoost, Nonlinear Risk DynamicsAbstract
Corporate leverage is widely recognized as a fundamental determinant of financial stability, yet the mechanisms throughwhich indebtedness escalates bankruptcy risk remain insufficiently understood. Traditional distress prediction modelstypically assume linear and additive relationships, potentially understating nonlinear amplification effects that emerge inhigh-leverage regimes. Using firm-level financial ratio data, nonlinear ensemble learning methods are employed toevaluate the leverage–distress relationship under rare-event conditions. Predictive performance is compared against alogistic regression benchmark using balanced metrics robust to class imbalance. Gradient boosting demonstratessuperior performance, indicating that financial distress risk is characterized by nonlinear and interaction-drivendynamics. Model interpretability analysis further reveals that leverage-related variables account for a substantialproportion of predictive importance and exhibit identifiable tipping points beyond whichbankruptcy probability increasesdisproportionately. Moreover, leverage effects intensify when profitability weakens, suggesting conditional riskamplification consistent with financial fragility and debt-overhang theories. By integrating ensemble learning withexplainable artificial intelligence, the analysis provides evidence of nonlinear leverage thresholds while preservingeconomic interpretability. The findings contribute to capital structure research by highlighting the importance of
threshold-dependent and interaction-based risk mechanisms in corporate distress modeling.
Downloads
References
Ben Jabeur, S., Stef, N., & Carmona, P. (2023).Bankruptcy prediction using the XGBoost algorithm and variable
importance feature engineering.Computational Economics,61(2), 715-741.
Bhatore, S., Mohan, L., & Reddy, Y. R. (2020).Machine learning techniques for credit risk evaluation: a systematic
literature review.Journal of Banking and Financial Technology,4(1), 111-138.
Borchert, P., Coussement, K., De Caigny, A., & De Weerdt, J. (2023). Extending business failure prediction models
with textual website content using deep learning.European Journal of Operational Research,306(1), 348-357.
Bracke, P., Datta, A., Jung, C., & Sen, S. (2019).Machine learning explainability in finance: an application to default
risk analysis.
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.
Bussmann, N., Giudici, P., Marinelli, D., & Papenbrock, J. (2021).Explainable machine learning in credit risk
management.Computational Economics,57(1), 203-216.
Carmona, P., Climent, F., & Momparler, A. (2019). Predicting failure in the US banking sector: An extreme gradient
boosting approach.International Reviewof Economics & Finance,61, 304-323.
Černevičienė, J., & Kabašinskas, A. (2024). Explainable artificial intelligence (XAI) in finance: a systematic literature
review.Artificial Intelligence Review,57(8), 216.
Climent, F., Momparler, A., & Carmona, P. (2019). Anticipating bank distress in the Eurozone: An extreme gradient
boosting approach.Journal of business research,101, 885-896.
Dasilas, A., & Rigani, A. (2024). Machine learning techniques in bankruptcy prediction: A systematic literature
review.Expert systems with applications,255, 124761.
De Bock, K. W., Coussement, K., & Lessmann, S. (2020). Cost-sensitive business failure prediction when
misclassification costs are uncertain: A heterogeneous ensemble selection approach.European Journal ofOperationalResearch,285(2), 612-630.
de Jesus, D. P., & da Nóbrega Besarria, C. (2023).Machine learning and sentiment analysis: Projecting bank
insolvency risk.Research in Economics,77(2), 226-238.
fedesoriano (2021).Company bankruptcy prediction[Data set]. Kaggle.
https://www.kaggle.com/datasets/fedesoriano/company-bankruptcy-prediction
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.
Haque, S. M., & Varghese, M. R. (2021).The COVID-19 impact on corporate leverage and financial fragility.
International Monetary Fund.
Sigrist, F., & Leuenberger, N. (2023). Machine learning for corporate default risk: Multi-period prediction, frailty
correlation, loan portfolios, and tail probabilities.European Journal of Operational Research,305(3), 1390-1406.
Smith, M., & Alvarez, F.(2022). Predicting firm-level bankruptcy in the Spanish economy using extreme gradient
boosting.Computational Economics,59(1), 263-295.
Tan, K. J. K., Zhou, Q., Pan, Z., & Faff, R. (2021).Business shocks and corporate leverage.Journal of Banking &
Finance,131, 106208.
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.
Wang, S., & Chi, G. (2024). Cost-sensitive stacking ensemblelearning for company financial distress
prediction.Expert Systems with Applications,255, 124525.
Weber, P., Carl, K. V., & Hinz, O. (2024).Applications of Explainable Artificial Intelligence in Finance—a systematic
review of Finance, Information Systems, and Computer Science literature: P. Weber et al.Management ReviewQuarterly,74(2), 867-907.
