Bankruptcy Prediction and Firm Heterogeneity
Revista Facultad de Ciencias Económicas · 29.05.2026 · 34 (1)
DOI: 10.18359/rfce.7746 ↗Kurz gefasst
Fachartikel in der Zeitschrift Revista Facultad de Ciencias Económicas, online erschienen am 29.05.2026. Verfasst von Yuly Andrea Franco und 1 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
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.
Zitieren
APA
Franco, Y. A., & Bolaños, J. F. (2026). Bankruptcy Prediction and Firm Heterogeneity. Revista Facultad de Ciencias Económicas, 34(1). https://doi.org/10.18359/rfce.7746
Vancouver
Franco YA, Bolaños JF. Bankruptcy Prediction and Firm Heterogeneity. Revista Facultad de Ciencias Económicas. 2026;34(1). doi:10.18359/rfce.7746
BibTeX
@article{Franco2026,
author = {Franco, Yuly Andrea and Bolaños, Jaime Flórez},
title = {Bankruptcy Prediction and Firm Heterogeneity},
journal = {Revista Facultad de Ciencias Económicas},
year = {2026},
volume = {34},
number = {1},
doi = {10.18359/rfce.7746}
}
EUVIMED