Falco J. Bargagli-Stoffi, Fabio Incerti, Massimo Riccaboni, Armando Rungi
arXiv 13 Jun 2023 · Econometrics · publishedIndustrial and Corporate Change (2023) · 7 citations (OpenAlex)
arXiv:2306.08165 · PDF · DOI · OpenAlex · Extracted main text
In this contribution, we propose machine learning techniques to predict zombie firms. First, we derive the risk of failure by training and testing our algorithms on disclosed financial information and non-random missing values of 304,906 firms active in Italy from 2008 to 2017. Then, we spot the highest financial distress conditional on predictions that lies above a threshold for which a combination of false positive rate (false prediction of firm failure) and false negative rate (false prediction of active firms) is minimized. Therefore, we identify zombies as firms that persist in a state of financial distress, i.e., their forecasts fall into the risk category above the threshold for at least three consecutive years. For our purpose, we implement a gradient boosting algorithm (XGBoost) that exploits information about missing values. The inclusion of missing values in our predictive model is crucial because patterns of undisclosed accounts are correlated with firm failure. Finally, we show that our preferred machine learning algorithm outperforms (i) proxy models such as Z-scores and the Distance-to-Default, (ii) traditional econometric methods, and (iii) other widely used machine learning techniques. We provide evidence that zombies are on average less productive and smaller, and that they tend to increase in times of crisis. Finally, we argue that our application can help financial institutions and public authorities design evidence-based policies-e.g., optimal bankruptcy laws and information disclosure policies.
appendix boundary found by appendix_command · 73% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Andrews, D., McGowan, M. A., Millot, V., et al (2017) Confronting the zombies: Policies for productivity revival | 0.928 | 4 | 4 | 100% |
| 2 | Andrews, D., Petroulakis, F., Feb (2019) Breaking the shackles: Zombie firms, weak banks and depressed restructuring in Europe | 0.928 | 4 | 3 | 100% |
| 3 | McGowan, M. A., Andrews, D., Millot, V (2018) The walking dead? zombie firms and productivity performance in oecd countries | 0.909 | 8 | 4 | 75% |
| 4 | Caballero, R. J., Hoshi, T., Kashyap, A. K (2008) Zombie lending and depressed restructuring in japan | 0.843 | 4 | 4 | 75% |
| 5 | Josse, J., Prost, N., Scornet, E., Varoquaux, G (2019) On the consistency of supervised learning with missing values | 0.843 | 4 | 3 | 75% |
| 6 | Schivardi, F., Sette, E., Tabellini, G (2021) Credit misallocation during the european financial crisis credit misallocation during the crisis | 0.737 | 4 | 3 | 50% |
| 7 | Banerjee, R., Hofmann, B (2018) The rise of zombie firms: causes and consequences | 0.737 | 3 | 3 | 67% |
| 8 | Bank of Korea (2013) Financial stability report | 0.737 | 3 | 3 | 67% |
| 9 | Chen, T., Guestrin, C (2016) Xgboost: A scalable tree boosting system | 0.737 | 3 | 3 | 67% |
| 10 | Twala, B., Jones, M., Hand, D. J (2008) Good methods for coping with missing data in decision trees | 0.737 | 3 | 3 | 67% |
Showing the top 10 of 109 scored citations.