Abstract

In this paper, bankruptcy prediction has been determined an important and widely studied topic. The goal of this study is to predict enterprise insolvency before the bankruptcy using artificial neural networks, to enable all parties to take remedial action. Artificial neural networks are widely used in finance and insurance problems. Generalized Regression Neural Network (GRNN) is used to evaluate the predictor variable used to predict the insolvency. The most important predictor variable influencing insolvency is consistently having the largest regression. Results showed that the most affecting factor in enterprise insolvency evaluation is the net income, total equity capital, cost of sales, sales, cash flows and loans. The Feed-forward back propagation neural network is used to predict the bankruptcy. The results of applying feed-forward back propagation neural network methodology to predict financial distress based upon selected financial ratios show abilities of the network to learn the patterns corresponding to financial distress of the enterprise. Artificial neural networks show significant signs for providing early warning signals and solvency monitoring. The proposed neural network is evaluated using confusion matrices.

Authors and Affiliations