With One Shot, Which Bullet Would You Use?: Market versus Accounting Data in Bankruptcy Prediction - Part III (The Strong Case of the Use of Neural Networks in Bankruptcy Prediction)

The International Journal of Finance, 26(4), 2015

75 Pages Posted: 3 Apr 2016

See all articles by Giovanni Fernandez

Giovanni Fernandez

Stetson University

Arun J. Prakash

Florida International University (FIU) - Department of Finance; Florida International University

Suchi Mishra

Florida International University (FIU) - Department of Finance

Date Written: April 1, 2016

Abstract

In this paper, we test the predictive power of neural networks to predict corporate bankruptcy. In contrast with the previous literature, we not only use nontraditional models and employ accounting ratios, but also market and microstructure variables. The most important findings are that market variables alone are best at correctly classifying bankrupt firms, the multi-layer perceptron is the preferable neural network model due to the nonlinear relation between predictive variables and bankruptcy, and the multi-layer perceptron has higher classification rates for all different input sets and years.

Suggested Citation

Fernandez, Giovanni and Prakash, Arun Jai and Mishra, Suchismita, With One Shot, Which Bullet Would You Use?: Market versus Accounting Data in Bankruptcy Prediction - Part III (The Strong Case of the Use of Neural Networks in Bankruptcy Prediction) (April 1, 2016). The International Journal of Finance, 26(4), 2015. Available at SSRN: https://ssrn.com/abstract=2757764

Giovanni Fernandez (Contact Author)

Stetson University ( email )

Gulfport, FL 33707
United States

Arun Jai Prakash

Florida International University (FIU) - Department of Finance ( email )

University Park
11200 SW 8th Street
Miami, FL 33199
United States

Florida International University ( email )

Miami, FL 33199
United States

Suchismita Mishra

Florida International University (FIU) - Department of Finance ( email )

University Park
11200 SW 8th Street
Miami, FL 33199
United States

Register to save articles to
your library

Register

Paper statistics

Downloads
76
Abstract Views
724
rank
324,147
PlumX Metrics