摘要：Commercial banks are facing increasingly complex enterprise loan customers and businesses. It is important for banks' enterprise loan business to efficiently assess credit risks. Our study builds an enterprise credit risk assessment model based on the state and constraint of bank and customer, and get empirical researches with RF, SVM and DT algorithms. The results show that our model has excellent performance with accuracy 99 % and great characteristic importance in the evaluation of enterprise credit risk. The study can provide important decision-making reference for bank loan business and enrich the theoretical system of bank credit risk research.
关键词：Credit risk assessment;state and constraint;enterprise loan;machine learning
