Evaluating Consumer Loans using Neural Networks

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.