Credit Risk Assessment of Power Material Procurement Suppliers Based on Logistic Regression Algorithm

Under the background of global economy, the supply chain of power industry is facing increasing credit risk. The purpose of this study is to establish a scientific supplier credit risk evaluation model by applying Logistic regression algorithm to quantitatively evaluate the credit risk of power material suppliers. In the research process, firstly, key data such as suppliers’ historical credit records, financial status and their position in the supply chain are collected, and these factors are quantitatively analyzed in detail to determine their impact on suppliers’ credit risk. Then, the Logistic regression model is trained by using these data, and the weight of each factor is analyzed through the model coefficients, and finally a quantitative tool that can predict the future credit risk of suppliers is formed. When the regularization parameter is 1.0, the model performs best in accuracy and AUC-ROC (area under the curve-receiver operating characteristic).Through the implementation of this evaluation model, power enterprises can not only improve the management efficiency of suppliers, but also maintain their core competitiveness in the highly competitive market.