CaltechAUTHORS
  A Caltech Library Service

Bankruptcy prediction for credit risk using neural networks: A survey and new results

Atiya, Amir F. (2001) Bankruptcy prediction for credit risk using neural networks: A survey and new results. IEEE Transactions on Neural Networks, 12 (4). pp. 929-935. ISSN 1045-9227. https://resolver.caltech.edu/CaltechAUTHORS:20170408-135833952

[img] PDF - Published Version
See Usage Policy.

87Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20170408-135833952

Abstract

The prediction of corporate bankruptcies is an important and widely studied topic since it can have significant impact on bank lending decisions and profitability. This work presents two contributions. First we review the topic of bankruptcy prediction, with emphasis on neural-network (NN) models. Second, we develop an NN bankruptcy prediction model. Inspired by one of the traditional credit risk models developed by Merton (1974), we propose novel indicators for the NN system. We show that the use of these indicators in addition to traditional financial ratio indicators provides a significant improvement in the (out-of-sample) prediction accuracy (from 81.46% to 85.5% for a three-year-ahead forecast).


Item Type:Article
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.1109/72.935101DOIArticle
http://ieeexplore.ieee.org/document/935101/PublisherArticle
Additional Information:© 2001 IEEE. Manuscript received February 13, 2001; revised March 16, 2001 and March 25, 2001. The author would like to acknowledge the useful discussions with P. Sondhi. The author would also like to acknowledge the support of NSF's Engineering Research Center at Caltech.
Funders:
Funding AgencyGrant Number
NSFUNSPECIFIED
Subject Keywords:Neural networks, Predictive models, Portfolios, Accuracy, Economic indicators, Profitability, Nonhomogeneous media, Asia, Regulators, Risk management
Issue or Number:4
Record Number:CaltechAUTHORS:20170408-135833952
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20170408-135833952
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:75897
Collection:CaltechAUTHORS
Deposited By: 1Science Import
Deposited On:14 Apr 2017 19:39
Last Modified:03 Oct 2019 16:55

Repository Staff Only: item control page