Small and micro enterprises are pivotal in national economic and social development. To foster their growth, managing their credit risks scientifically is crucial. This study starts by examining the credit information of these enterprises. We use imbalanced sample processing algorithms to ensure a balanced representation of minority-class samples. Then, a machine learning classifier is employed to identify key factors contributing to these enterprises' low credibility. Based on these factors, an XGBoost scoring card model is developed. The study reveals: firstly, the integration of the SMOTE algorithm with the XGBoost model exhibits certain performance advantages in handling imbalanced datasets; secondly, trustworthy financial information remains at the heart of crucial risk determinants; thirdly, the XGBoost scoring card model based on significant features effectively enhances the accuracy of credit risk assessment. These insights provide both theoretical references and practical tools for enhancing the robustness of small and micro enterprises, facilitating early warnings on credit risks, and refining financing efficiency.
Keywords: Imbalanced processing; Machine learning; Scorecard model; Small and micro enterprises.
© 2024 The Author(s).