Bankruptcy Prediction: A Comparison of Some Statistical and Machine Learning Techniques

Banco de Mexico Working Paper No. 2009-18

35 Pages Posted: 20 Dec 2009

See all articles by Tonatiuh Pena Centeno

Tonatiuh Pena Centeno

German Center for Neurodegenerative Diseases (DZNE)

Serafin Martinez Jaramillo

Bank of Mexico

Bolanle Abudu

affiliation not provided to SSRN

Date Written: December 17, 2009

Abstract

We are interested in forecasting bankruptcies in a probabilistic way. Specifcally, we compare the classifcation performance of several statistical and machine-learning techniques, namely discriminant analysis (Altman's Z-score), logistic regression, least-squares support vector machines and different instances of Gaussian processes (GP's) - that is GP's classifiers, Bayesian Fisher discriminant and Warped GP's. Our contribution to the field of computational finance is to introduce GP's as a potentially competitive probabilistic framework for bankruptcy prediction. Data from the repository of information of the US Federal Deposit Insurance Corporation is used to test the predictions.

Keywords: Bankruptcy prediction, Artificial intelligence, Supervised learning, Gaussian processes, Z-score

JEL Classification: C11, C14, C45

Suggested Citation

Pena Centeno, Tonatiuh and Martinez Jaramillo, Serafin and Abudu, Bolanle, Bankruptcy Prediction: A Comparison of Some Statistical and Machine Learning Techniques (December 17, 2009). Banco de Mexico Working Paper No. 2009-18, Available at SSRN: https://ssrn.com/abstract=1525947 or http://dx.doi.org/10.2139/ssrn.1525947

Tonatiuh Pena Centeno (Contact Author)

German Center for Neurodegenerative Diseases (DZNE) ( email )

Venusberg-Campus 1, Building 99
Bonn, 53127
Germany

Serafin Martinez Jaramillo

Bank of Mexico ( email )

Av. 5 de Mayo # 1
Colonia Centro
Mexico City, D. F. 06059
Mexico

Bolanle Abudu

affiliation not provided to SSRN ( email )

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
432
Abstract Views
2,467
rank
79,977
PlumX Metrics