Analysis and Research on Credit Risk Factors of Listed Companies in China Based on CVM-MLP

Authors:

Abstract
At present, the liquidity requirement of listed companies' loan funds is high, and the importance of adequate assessment of SME credit risk factors is increasingly significant. In this paper, the ANN-MLP (Artificial Neural Network-Multilayer Perceptron) model is used to evaluate the credit risk of listed companies in China from five aspects of corporate solvency, profitability, operational capacity, growth capacity, and cash flow based on the internal characteristics of listed companies. Fifteen representative secondary indicators are selected, and the CVM(Coefficient of Variation Method) algorithm is used to reduce the dimension of the indicators. The accuracy of ANN training results is 95%, which has high robustness. The results show that the contribution value of the fixed asset turnover rate is the highest (0.367), which provides an essential reference for commercial bank credit decisions.