Research on SMEs Credit Risk Prediction Based on Decision Tree and Random Forest

SMEs (small and medium enterprises) are more prone to default due to the problem of information asymmetry with banks and a lack of suitable collateral. Banks face both opportunities and challenges due to the high demand for loans from SMEs, and identifying credit risk has become their primary concern. Restructured sentence for clarity and concision. This paper aims to predict the credit loan status of SMEs in Chinese banks by utilizing an open data set provided by the Digital China Innovation Competition. Decision tree and random forest models are used to construct a classification model, which is then analyzed along with its important attributes. Results indicate that both pruning decision tree and random forest models are effective in identifying credit risks for SMEs.