Issue |
SHS Web Conf.
Volume 218, 2025
2025 2nd International Conference on Development of Digital Economy (ICDDE 2025)
|
|
---|---|---|
Article Number | 02016 | |
Number of page(s) | 8 | |
Section | Finance Tech Advances: Impacts and Innovations | |
DOI | https://doi.org/10.1051/shsconf/202521802016 | |
Published online | 03 July 2025 |
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
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.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.