Benchmarking Machine Learning Models to Predict Corporate Bankruptcy
This work addresses the problem of predicting corporate bankruptcy for financial analysts and investors, but it is incremental as it benchmarks existing models without introducing new methods.
The study benchmarked machine learning models to predict corporate bankruptcy using data from 2,585 bankruptcies from 1990 to 2019, finding that gradient boosted trees performed best for one-year-ahead forecasts and survival random forests captured large dollar profits in a credit competition model.
Using a comprehensive sample of 2,585 bankruptcies from 1990 to 2019, we benchmark the performance of various machine learning models in predicting financial distress of publicly traded U.S. firms. We find that gradient boosted trees outperform other models in one-year-ahead forecasts. Variable permutation tests show that excess stock returns, idiosyncratic risk, and relative size are the more important variables for predictions. Textual features derived from corporate filings do not improve performance materially. In a credit competition model that accounts for the asymmetric cost of default misclassification, the survival random forest is able to capture large dollar profits.