Bankruptcy Prediction and Firm Heterogeneity
Insights from a Meta-Analysis
Resumen
This study uses a meta-analytic approach based on random-effects models to examine the effectiveness of Machine Learning (ML) techniques in predicting business bankruptcies. Sixty-four studies were analyzed and categorized by two key performance metrics: Area Under the Curve (AUC) and Accuracy (ACC). The three main findings are: (1) While absolute performance differences appear small, significant variability exists across ML models depending on the context; (2) no statistically significant differences were found between the predictive capabilities of AUC and ACC in classifying firms as bankrupt or non-bankrupt; and (3) substantial heterogeneity among studies was confirmed, driven by firm characteristics, industry, and methodological differences. These results emphasize the importance of customizing ML models to specific datasets and highlight how contextual factors shape predictive accuracy. This study contributes to the literature by addressing the underexplored role of firm heterogeneity and offering actionable insights for practitioners, policymakers, and researchers aiming to improve financial risk prediction.
Descargas
Referencias bibliográficas
Altman, E. (1968). Financial ratios, discriminant analysis, and the prediction of business bankruptcy. The Journal of Finance, 23(4), 589–609. https://doi.org/10.1111/j.1540-6261.1968.tb00843.x
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
Bolaños Díaz, R., & Calderón Cahua, M. (2014). Introducción al meta-análisis tradicional. Revista de Gastroenterología del Perú, 34(1), 45–51.
Borenstein, M., Hedges, L. V., Higgins, J. P. T., & Rothstein, H. R. (2009). Effect sizes on binary data. In Introduction to meta-analysis (pp. 33–39). John Wiley & Sons. https://doi.org/10.1002/9780470743386
Botella, J., & Zamora, Á. (2017). El meta-análisis: Una metodología para la investigación en educación. Educación XX1, 20(2), 17–38. https://doi.org/10.5944/educxx1.19030
Cielen, A., Peeters, L., & Vanhoof, K. (2004). Bankruptcy prediction using data envelopment analysis. European Journal of Operational Research, 154(2), 526–532. https://doi.org/10.1016/S0377-2217(03)00186-3
Escrig, S. V. J., Llueca, A., Granel-Villach, L., & Bellver-Oliver, M. (2021). Meta-analysis: A basic way to understand and interpret its evidence. Revista de Senología y Patología Mamaria, 34, 44–51. https://doi.org/10.1016/j.senol.2020.05.007
Fernandez-Chinguel, J. E., Zafra-Tanaka, J., Goicochea-Lugo, S., Peralta, C., & Taype-Rondan, A. (2019). Basic aspects of reading systematic reviews and interpreting meta-analyses. Acta Médica Peruana, 36(2), 157–169. https://doi.org/10.35663/amp.2019.362.818
Franco, Y. A. (2022). A bibliometric analysis of business bankruptcy prediction using machine learning. ODEON - Observatorio de Economía y Operaciones Numéricas, 22, 87–126. https://doi.org/10.18601/17941113.n22.04
Franco, Y. A. (2023). Machine learning applied to financial distress and business bankruptcy: A literature review. In J. Martínez Garcés (Ed.), Advances in scientific research (pp. 277–329). AUNAR.
Heo, J., & Yong Yang, J. (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
Huang, Y.-P., & Yen, M.-F. (2019). A new perspective of performance comparison among machine learning algorithms for financial distress prediction. https://doi.org/10.2139/ssrn.3437863
Khademolqorani, S., Zeinal Hamadani, A., & Mokhatab Rafiei, F. (2015). A hybrid analysis approach to improve financial distress forecasting: Empirical evidence from Iran. Mathematical Problems in Engineering, 2015, 1–9. https://doi.org/10.1155/2015/178197
Lahmiri, S., & Bekiros, S. (2019). Can machine learning approaches predict business bankruptcy? Evidence from a qualitative experimental design. Quantitative Finance, 19, 1–9. https://doi.org/10.1080/14697688.2019.1588468
Le, H. H., & Viviani, J. L. (2018). Predicting bank failure: An improvement by implementing a machine-learning approach to classical financial ratios. Research in International Business and Finance, 44, 16–25. https://doi.org/10.1016/j.ribaf.2017.07.104
Li, Z., Crook, J., & Andreeva, G. (2017). Dynamic prediction of financial distress using Malmquist DEA. Expert Systems with Applications, 80, 94–106. https://doi.org/10.1016/j.eswa.2017.03.017
Liang, D., Tsai, C. F., Dai, A. J., & Eberle, W. (2018). A novel classifier ensemble approach for financial distress prediction. Knowledge and Information Systems, 54(2), 437–462. https://doi.org/10.1007/s10115-017-1061-1
Sánchez-Meca, J. (1999). Meta-analysis for scientific research. In F. J. Sarabia (Ed.), Methodology for research in marketing and business management (pp. 173–201). Pirámide.
Sergas.es. (2018). Meta-analysis. https://www.sergas.es/Saude-publica/Documents/1930/11-Ayuda%20Meta-anlisis.pdf
Tirole, J. (1988). The theory of industrial organization. MIT Press.
| Estadísticas de artículo | |
|---|---|
| Vistas de resúmenes | |
| Vistas de PDF | |
| Descargas de PDF | |
| Vistas de HTML | |
| Otras vistas | |
Derechos de autor 2026 Revista Facultad de Ciencias Económicas
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-SinDerivadas 4.0.
