Research of Credit Grade Assessment for SMB Based on Multi-Layer SVM Classifier

摘要

It is very important to get financial supporting for Small and Medium Business(SMB) from the banks, which can set up a effective credit assessing system so that it can dispel misgiving of bank in the cause of the loaning to SMB. According to the credit grade assessment for SMB in practice and the related theories, a set of index system which assesses a SMB's credit grade is established. Basing on the index system, a multi-layer support vector machines (SVM) classifier is established to assess and classify the SMB' credit grade. In order to verify the effectiveness of the method, a real case is given and BP neural network is also used assess the same data. The experimental results show that multi-layer SVM classifier is effective in credit level assessment and achieves better performance than BP neural network.