Predicting Corporate Bankruptcies

104 Pages Posted: 18 Jul 2019

See all articles by Derek Snow

Derek Snow

FirmAI, UoA, NYU FRE; University of Auckland

Date Written: November 12, 2017


In this study, I present the use of non-linear models and accounting inputs to predict the occurrence of litigated bankruptcies and associated filing outcomes. The main purpose of this study is to identify the accounting patterns associated with bankruptcy. The filing outcomes include, among other things, how long the bankruptcy process will endure, whether the firm will successfully emerge after the bankruptcy period, whether the bankruptcy is tortuous and whether it will involve asset sales. The study highlights the importance of previously unidentified variables useful in predicting bankruptcies and bankruptcy outcomes. The study categorises predictor variables in accounting dimensions to empirically identify the importance of each dimension to the prediction tasks. The high-dimensionality of the gradient boosting machine allows us to identify and explain the nonlinear interactions between a wide range of variables to get a sense of the most important combinations.

Keywords: Bankruptcy prediction, Machine Learning, Corporate Default, Bankruptcy Outcomes

JEL Classification: C32, C38, C45, G33

Suggested Citation

Snow, Derek, Predicting Corporate Bankruptcies (November 12, 2017). Available at SSRN: or

Derek Snow (Contact Author)

FirmAI, UoA, NYU FRE ( email )

NYC, Cambridge, Auckland


University of Auckland ( email )

New Zealand

Here is the Coronavirus
related research on SSRN

Paper statistics

Abstract Views
PlumX Metrics