抽象的な

Research of risk assessment and prediction based on support vector machine

Dakai Li, Yu Li, Zhang Qi-Wen

Building a suitable credit risk evaluation model is very important, that is because loan business is one of the most important assets of commercial Banks. In this paper, we introduce a kind of learning algorithm which contains small sample learning and construct a new method which is called support vector machine (SVM). SVM is developed based on a new theory that is popular used in the field of intelligent learning system in recent years. The credit risk assessment model of commercial bank is established finally. By multiple discriminate analyses and the comparison of neural network model, confirms the validity and superiority of the method when be used in risk assessment.