Research on Credit Risk Assessment of Listed Companies in Technology Sector Based on Support Vector Machine Integration

Abstract

In recent years, the state vigorously support the development of science and technology enterprises, with the transformation of economy and the rapid development of science and technology, science and technology enterprises in our country's economic development play a more and more important role, but the science and technology enterprises are in growth period, exist in the process of the development of a lot of risk, so there are some problems in financing. For banks, credit evaluation of enterprises is very necessary, which can effectively reduce the credit risk of banks. Based on the establishment of the credit evaluation index system of listed companies in the science and technology sector, this paper screens out 12 indicators, uses support vector machine to classify the selected sample enterprises, and trains 10 sub-support vector machines. In order to improve the accuracy, the fuzzy integral based support vector machine ensemble method is used to classify enterprises. The results show that the classification accuracy of both training samples and test samples is improved, and the integrated classification accuracy is higher than that of a single support vector machine, which also shows the feasibility and effectiveness of the model.