Corporate Bankruptcy Prediction Using Machine Learning
Journal of Innovation and Development · 15.04.2026 · 15 (2) · 65-72
DOI: 10.54097/heb14966 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Innovation and Development, online erschienen am 15.04.2026. Verfasst von Jialu Chen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
As the advancement of machine learning, hundreds of methods have been proposed in solving corporate bankruptcy prediction problems. Facing with these options, decision-makers must decide the most effective methods. On the other hand, bankruptcy data usually involve high-dimensionality and extreme class imbalance, which may undermine the performance of classical models. This research designs and validates a systematic framework to address these issues, combining feature selection, sample rebalancing and machine learning model selection together. The study chooses five typical machine learning models, including Logistic Regression (LR), Support Vector machine (SVM), Decision Tree (DT), XGBoost (XGB) and Random Forest (RF). Also, this study designs the training and test data sets using a two-layered feature selection method, comparing two resampling methods and five classic machine learning models to form a final improved voting classifier with hyperparameters tuned. The experimental results confirm that XGB and RF, when combined with oversampling method, can provide the most robust prediction.
Zitieren
APA
Chen, J. (2026). Corporate Bankruptcy Prediction Using Machine Learning. Journal of Innovation and Development, 15(2), 65-72. https://doi.org/10.54097/heb14966
Vancouver
Chen J. Corporate Bankruptcy Prediction Using Machine Learning. Journal of Innovation and Development. 2026;15(2):65-72. doi:10.54097/heb14966
BibTeX
@article{Chen2026,
author = {Chen, Jialu},
title = {Corporate Bankruptcy Prediction Using Machine Learning},
journal = {Journal of Innovation and Development},
year = {2026},
volume = {15},
number = {2},
pages = {65--72},
doi = {10.54097/heb14966}
}
EUVIMED