Evaluating Consumer Loans using Neural Networks

39 Pages Posted: 19 Jun 2002  

Davinder K. Malhotra

Philadelphia University

Rashmi Malhotra

Saint Joseph's University

Date Written: January 2001

Abstract

A number of credit-scoring models that accurately classify consumer loan applications have been developed to aid traditional judgmental methods. This study compares the performance of multiple discriminant analysis and neural networks in identifying potential loan. While there is not a significant improvement in the performance of neural network over discriminant analysis model in identifying good credit loans, the neural network models consistently perform better than the multiple discriminant analysis models in identifying potential problem loans. To alleviate the problem of bias in the training set and to examine the robustness of neural network classifiers in identifying problem loans, we cross-validate our results through seven different samples of the data.

Suggested Citation

Malhotra, Davinder K. and Malhotra, Rashmi, Evaluating Consumer Loans using Neural Networks (January 2001). EFMA 2002 London Meetings. Available at SSRN: https://ssrn.com/abstract=314396 or http://dx.doi.org/10.2139/ssrn.314396

Davinder K. Malhotra (Contact Author)

Philadelphia University ( email )

Schoolhouse Lane and Henry Avenue
School of Business Administration
Philadelphia, PA 19144
United States

Rashmi Malhotra

Saint Joseph's University ( email )

5600 City Avenue,
Philadelphia, PA 19131
United States

Paper statistics

Downloads
842
Rank
21,918
Abstract Views
3,574