Credit Risk Assessment of Chinese Listed Companies Based on SVM Improved by Shuffled Frog Leaping Algorithm

In the previous studies, when using Support Vector Machine Model to predict corporate credit risk, a problem of improper parameter values was often existed that lead to low classification accuracy. This article introduces the Shuffled frog leaping algorithm to improve the parameters of the SVM, and selects the relevant data of listed companies in China to build the model. The results show that the SVM improved by the Shuffled Frog Leaping Algorithm has higher accuracy and better effects on the credit risk assessment of listed companies.