Journal of Credit Risk
ISSN:
1744-6619 (print)
1755-9723 (online)
Editor-in-chief: Linda Allen and Jens Hilscher
Understanding and predicting systemic corporate distress: a machine-learning approach
Need to know
- We propose a new definition for system-wide corporate distress events and provide a novel database of corporate distress events covering the last three decades and 55 advanced and emerging markets.
- We find corporate distress generally is followed by slower economic growth. However, not all corporate distress events lead to systemic corporate nor financial crises.
- We construct a machine-learning based model to forecast systemic corporate distress with a forecast horizon of 4-quarters. The early-warning system generates timely warnings and identifies sources of vulnerabilities using Shapley value decomposition.
Abstract
evel probabilities of default, covering 55 economies and spanning the last three decades. Systemic corporate distress is identified by elevated probabilities of default across a large portion of the firms in an economy. A machine-learning-based earlywarning system is constructed to predict the risk of systemic distress in one year’s time. Our results show that credit expansion, monetary policy tightening, overvalued stock prices and debt-linked balance-sheet weaknesses predict corporate distress.We also find that systemic corporate distress events are associated with contractions in gross domestic product. Their impacts are milder than those of financial crises.
Copyright Infopro Digital Limited. All rights reserved.
As outlined in our terms and conditions, https://www.infopro-digital.com/terms-and-conditions/subscriptions/ (point 2.4), printing is limited to a single copy.
If you would like to purchase additional rights please email info@risk.net
Copyright Infopro Digital Limited. All rights reserved.
You may share this content using our article tools. As outlined in our terms and conditions, https://www.infopro-digital.com/terms-and-conditions/subscriptions/ (clause 2.4), an Authorised User may only make one copy of the materials for their own personal use. You must also comply with the restrictions in clause 2.5.
If you would like to purchase additional rights please email info@risk.net
