Applying artificial neural networks to bank-decision simulations

Abstract

Artificial neural networks are nonlinear models that can be trained to extract hidden structures and relationships that govern the data. They can be used for analyzing relationships among economic and financial phenomena. This paper presents research on applying a back propagation algorithm to firm classification. Experiments were provided for three neural network architectures by applying training and testing samples constructed from actual data of the firms that applied for credit in regional banks for the period 1994–97. To study the effect of proportion between the number of firms that obtained and did not obtain credit, three proportions of the training and testing set compositions were created: 1:1, 2:1, and 4:1. Classification accuracy was evaluated in terms of errors made by the neural networks.