A machine learning and Anova-based approach to model financial predictors for corporate failure in imbalanced dataset
The case of Taiwan
Bibliographic Data
| ID | 22189422 |
|---|---|
| Authors | Borislava Toleva (0000-0001-9335-6927, Sofia University "St. Kliment Ohridski"), Ivan Ivanov (0000-0001-7519-9657, Sofia University "St. Kliment Ohridski"), Vincent J Hooper (0000-0001-6473-700X, Synergy University Dubai), Vincent Hooper |
| Year | 2025 |
| Volume | 9 |
| Issue | 1 |
| Pages | 10072 |
| Publication date | 2025-01-06 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Journal of Infrastructure Policy and Development (JOURNAL) |
| Journal identifiers | ISSN: 2572-7923 • E-ISSN: 2572-7931 |
| Publisher | EnPress Publisher (PUBLISHER) |
| DOI | 10.24294/jipd10072 |
| OpenAlex | W4406078483 |
| Language | EN |
| References cited | 5 |
This study meticulously explores the crucial elements precipitating corporate failures in Taiwan during the decade from 1999 to 2009. It proposes a new methodology, combining ANOVA and tuning the parameters of the classification so that its functional form describes the data best. Our analysis reveals the ten paramount factors, including Return on Capital ROA(C) before interest and depreciation, debt ratio percentage, consistent EPS across the last four seasons, Retained Earnings to Total Assets, Working Capital to Total Assets, dependency on borrowing, ratio of Current Liability to Assets, Net Value Per Share (B), the ratio of Working Capital to Equity, and the Liability-Assets Flag. This dual approach enables a more precise identification of the most instrumental variables in leading Taiwanese firms to bankruptcy based only on financial rather than including corporate governance variable. By employing a classification methodology adept at addressing class imbalance, we substantiate the significant influence these factors had on the incidence of bankruptcy among Taiwanese companies that rely solely on financial parameters. Thus, our methodology streamlines variable selection from 95 to 10 critical factors, improving bankruptcy prediction accuracy and outperforming Liang's 2016 results
Business · Econometrics · Economics · Machine learning · Computer Science · Financial Distress and Bankruptcy Prediction · Imbalanced Data Classification Techniques · Artificial Intelligence
| Highly cited | No |
|---|