Research on Credit Risk Evaluation System for Small and Medium-Sized Enterprises Based on Machine Learning Model

School of Public Finance and Taxation, Southwestern University of Finance and Economics, Chengdu, Sichuan, 610074, China

^* Corresponding author: 42203050@swufe.edu.cn

Abstract

Corporate credit ratings are crucial for enterprise development, reflecting financing capabilities, business expansion potential, tax payment capacity, and corporate reputation. Credit is a fundamental prerequisite for enterprises to engage in market activities. A favorable credit standing can facilitate the establishment of stable cooperative relationships and lay a foundation for business operations and decision-making. This study focuses on credit risk evaluation for small and medium-sized enterprises (SMEs) and employs machine learning models to predict credit ratings using public datasets. The research looks into applying multiple machine learning techniques, such as Logistic Regression, Decision Tree, Random Forest, LightGBM, CatBoost, and Multilayer Perceptron (MLP), to determine the crucial factors that impact credit risk. The results show that the LightGBM-based SME credit rating model is more adaptable than other models. Analysis of the contribution degrees of evaluation indicators reveals that firm size, performance, and employee welfare stability are crucial in credit risk assessment. This helps financial institutions and enterprises make more precise decisions by accurately evaluating SME credit and identifying risks.