Research on credit risk of commercial banks based on multiple logistic model

This paper establishes a bank credit decision-making system for small and medium-sized enterprises. This paper quantifies the risk of enterprises with existing credit records and reputation ratings and establishes a risk rating model. The specific financial situation of 123 enterprises with credit records and credit rating is quantified and a model is established. In this paper, a large number of original data are processed and integrated by EXCEL and MATLAB software to get six indexes, and then three representative principal component factors are extracted by principal component analysis, which are used as independent variables for binary Logistic regression analysis, the evaluation of whether the enterprise is in breach of contract is obtained, the default screening model is established, the grade of the enterprise in breach of contract is rated as IV, and then the enterprise without default is analyzed by multivariate ordered Logistic regression analysis. Establish a risk level refinement model to further refine the non-default corporate rating, that is, I-level, II-level and III-level.