Advanced Default Risk Prediction in Small and Medum-Sized Enterprises Using Large Language Models
Predicting default risk in commercial bills for small and medium-sized enterprises (SMEs) is crucial, as these enterprises represent one of the largest components of a nation’s economic structure, and their financial stability can impact systemic financial risk. However, data on the commercial bills...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/5/2733 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850225334830497792 |
|---|---|
| author | Haonan Huang Jing Li Chundan Zheng Sikang Chen Xuanyin Wang Xingyan Chen |
| author_facet | Haonan Huang Jing Li Chundan Zheng Sikang Chen Xuanyin Wang Xingyan Chen |
| author_sort | Haonan Huang |
| collection | DOAJ |
| description | Predicting default risk in commercial bills for small and medium-sized enterprises (SMEs) is crucial, as these enterprises represent one of the largest components of a nation’s economic structure, and their financial stability can impact systemic financial risk. However, data on the commercial bills of SMEs are scarce and challenging to gather, which has impeded research on risk prediction for these businesses. This study aims to address this gap by leveraging 38 multi-dimensional, non-financial features collected from 1972 real SMEs in China to predict bill default risk. We identified the most influential factors among these 38 features and introduced a novel prompt-based learning framework using large language models for risk assessment, benchmarking against seven mainstream machine learning algorithms. In the experiments, the XGBoost algorithm achieved the best performance on the Z-Score standardized dataset, with an accuracy of 81.42% and an F1 score of 80%. Additionally, we tested both the standard and fine-tuned versions of the large language model, which yielded accuracies of 75% and 82.1%, respectively. These results indicate that the proposed framework has significant potential for predicting risks in SMEs and offers new insights for related research. |
| format | Article |
| id | doaj-art-e754f6f0524042a7b8c245f7707bb12e |
| institution | OA Journals |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-e754f6f0524042a7b8c245f7707bb12e2025-08-20T02:05:23ZengMDPI AGApplied Sciences2076-34172025-03-01155273310.3390/app15052733Advanced Default Risk Prediction in Small and Medum-Sized Enterprises Using Large Language ModelsHaonan Huang0Jing Li1Chundan Zheng2Sikang Chen3Xuanyin Wang4Xingyan Chen5School of Computing and Artificial Intelligence, Southwestern University of Finance and Economics, Chengdu 610074, ChinaSchool of Computing and Artificial Intelligence, Southwestern University of Finance and Economics, Chengdu 610074, ChinaSchool of Computing and Artificial Intelligence, Southwestern University of Finance and Economics, Chengdu 610074, ChinaSchool of Computing and Artificial Intelligence, Southwestern University of Finance and Economics, Chengdu 610074, ChinaBusiness School, Beijing Normal University, Beijing 100875, ChinaSchool of Computing and Artificial Intelligence, Southwestern University of Finance and Economics, Chengdu 610074, ChinaPredicting default risk in commercial bills for small and medium-sized enterprises (SMEs) is crucial, as these enterprises represent one of the largest components of a nation’s economic structure, and their financial stability can impact systemic financial risk. However, data on the commercial bills of SMEs are scarce and challenging to gather, which has impeded research on risk prediction for these businesses. This study aims to address this gap by leveraging 38 multi-dimensional, non-financial features collected from 1972 real SMEs in China to predict bill default risk. We identified the most influential factors among these 38 features and introduced a novel prompt-based learning framework using large language models for risk assessment, benchmarking against seven mainstream machine learning algorithms. In the experiments, the XGBoost algorithm achieved the best performance on the Z-Score standardized dataset, with an accuracy of 81.42% and an F1 score of 80%. Additionally, we tested both the standard and fine-tuned versions of the large language model, which yielded accuracies of 75% and 82.1%, respectively. These results indicate that the proposed framework has significant potential for predicting risks in SMEs and offers new insights for related research.https://www.mdpi.com/2076-3417/15/5/2733large language modelcommercial bill defaultfinancial credit risksSMEs |
| spellingShingle | Haonan Huang Jing Li Chundan Zheng Sikang Chen Xuanyin Wang Xingyan Chen Advanced Default Risk Prediction in Small and Medum-Sized Enterprises Using Large Language Models Applied Sciences large language model commercial bill default financial credit risks SMEs |
| title | Advanced Default Risk Prediction in Small and Medum-Sized Enterprises Using Large Language Models |
| title_full | Advanced Default Risk Prediction in Small and Medum-Sized Enterprises Using Large Language Models |
| title_fullStr | Advanced Default Risk Prediction in Small and Medum-Sized Enterprises Using Large Language Models |
| title_full_unstemmed | Advanced Default Risk Prediction in Small and Medum-Sized Enterprises Using Large Language Models |
| title_short | Advanced Default Risk Prediction in Small and Medum-Sized Enterprises Using Large Language Models |
| title_sort | advanced default risk prediction in small and medum sized enterprises using large language models |
| topic | large language model commercial bill default financial credit risks SMEs |
| url | https://www.mdpi.com/2076-3417/15/5/2733 |
| work_keys_str_mv | AT haonanhuang advanceddefaultriskpredictioninsmallandmedumsizedenterprisesusinglargelanguagemodels AT jingli advanceddefaultriskpredictioninsmallandmedumsizedenterprisesusinglargelanguagemodels AT chundanzheng advanceddefaultriskpredictioninsmallandmedumsizedenterprisesusinglargelanguagemodels AT sikangchen advanceddefaultriskpredictioninsmallandmedumsizedenterprisesusinglargelanguagemodels AT xuanyinwang advanceddefaultriskpredictioninsmallandmedumsizedenterprisesusinglargelanguagemodels AT xingyanchen advanceddefaultriskpredictioninsmallandmedumsizedenterprisesusinglargelanguagemodels |