The Research on Credit Rating Evaluation Based on SVM and BNN

摘要

Credit rating evaluation is very important to the credit risk analysis and there are so many studies about it during the past few decades.In this paper we attempt to extend previous research in two directions.Firstly,we apply support vector machines (SVM),to the credit-rating evaluation problem and expect to improve evaluation accuracy by adopting this new algorithm.Secondly,we apply the results from previous research on neural network model interpretation to the credit-rating problem,and try to provide some insights into the credit-rating process.These studies can help users capture fundamental characteristics of different financial markets.