Benchmarking Machine Learning Models to Predict Corporate Bankruptcy

45 Pages Posted: 20 Oct 2022 Last revised: 15 Mar 2023

See all articles by Emmanuel Alanis

Emmanuel Alanis

Texas State University

Sudheer Chava

Georgia Institute of Technology - Scheller College of Business

Agam Shah

Georgia Institute of Technology - College of Computing

Multiple version iconThere are 2 versions of this paper

Date Written: August 15, 2022

Abstract

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.

Keywords: Corporate Bankruptcy, Machine Learning

JEL Classification: G33

Suggested Citation

Alanis, Emmanuel and Chava, Sudheer and Shah, Agam, Benchmarking Machine Learning Models to Predict Corporate Bankruptcy (August 15, 2022). Georgia Tech Scheller College of Business Research Paper No. 4249412, Available at SSRN: https://ssrn.com/abstract=4249412 or http://dx.doi.org/10.2139/ssrn.4249412

Emmanuel Alanis

Texas State University ( email )

San Marcos, TX 78666
United States

Sudheer Chava

Georgia Institute of Technology - Scheller College of Business ( email )

800 West Peachtree St.
Atlanta, GA 30308
United States

HOME PAGE: http://https://fintech.gatech.edu

Agam Shah (Contact Author)

Georgia Institute of Technology - College of Computing ( email )

Atlanta, GA 30332
United States

HOME PAGE: http://https://shahagam4.github.io/

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
349
Abstract Views
1,010
Rank
156,879
PlumX Metrics