Estimation of Credit Risk for Business Firms of Nationalized Bank by Neural Network Approach

Financial credit risk assessment has gained a great deal of attention. Many different parties have an interest in credit risk assessment. Banking authorities are interested because it helps them to determine the overall strength of the banking system and its ability to handle adverse conditions. Due to the importance of credit risk analysis, many methods were widely applied to credit risk measurement tasks, from that Artificial Neural Network plays an important role for analyzing the credit default problem. Artificial neural networks represent an easily customizable tool for modeling learning behavior of agents and for studying a lot of problems very difficult to analyze with standard economic models ANN has many advantages over conventional methods of analysis. According to Shachmurove (2002), they have the ability to analyze complex patterns quickly and with a high degree of accuracy.The focus of this paper is to determine that a neural network is a suitable modelling technique for predicting the business firm loan is satisfactory or not. This paper shows that an ANN approach will classify the applicant as a default or not and predict a credit default allowance amount more closely aligned with the credit default expense incurred during the fiscal period than traditional management approaches to estimating the allowance. The results show that credit risk evaluation using Back propagation neural network and expert evaluation have the very good consistency Keywords― Financial Analysis, credit risk, NN algorithm, ROC Analysis