Research on credit risk of listed companies: a hybrid model based on TCN and DilateFormer
Abstract The ability to assess and manage corporate credit risk enables financial institutions and investors to mitigate risk, enhance the precision of their decision-making, and adapt their strategies in a prompt and effective manner. The growing quantity of data and the increasing complexity of in...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-86371-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585781441462272 |
|---|---|
| author | Chuanhe Shen Junzhe Wu |
| author_facet | Chuanhe Shen Junzhe Wu |
| author_sort | Chuanhe Shen |
| collection | DOAJ |
| description | Abstract The ability to assess and manage corporate credit risk enables financial institutions and investors to mitigate risk, enhance the precision of their decision-making, and adapt their strategies in a prompt and effective manner. The growing quantity of data and the increasing complexity of indicators have rendered traditional machine learning methods ineffective in enhancing the accuracy of credit risk assessment. Consequently, academics have begun to explore the potential of models based on deep learning. In this paper, we apply the concept of combining Transformer and CNN to the financial field, building on the traditional CNN-Transformer model’s capacity to effectively process local features, perform parallel processing, and handle long-distance dependencies. To enhance the model’s ability to capture financial data over extended periods and address the challenge of high-dimensional financial data, we propose a novel hybrid model, TCN-DilateFormer. This integration improves the accuracy of corporate credit risk assessment. The empirical study demonstrates that the model exhibits superior prediction accuracy compared to traditional machine learning assessment models, thereby offering a novel and efficacious tool for corporate credit risk assessment. |
| format | Article |
| id | doaj-art-6efbcb8a379b4613bc2341767893e0e3 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-6efbcb8a379b4613bc2341767893e0e32025-01-26T12:32:03ZengNature PortfolioScientific Reports2045-23222025-01-0115111810.1038/s41598-025-86371-7Research on credit risk of listed companies: a hybrid model based on TCN and DilateFormerChuanhe Shen0Junzhe Wu1Institute of Financial Engineering of Shandong Women’s UniversityCollege of Mathematics and Systems Science, Shandong University of Science and TechnologyAbstract The ability to assess and manage corporate credit risk enables financial institutions and investors to mitigate risk, enhance the precision of their decision-making, and adapt their strategies in a prompt and effective manner. The growing quantity of data and the increasing complexity of indicators have rendered traditional machine learning methods ineffective in enhancing the accuracy of credit risk assessment. Consequently, academics have begun to explore the potential of models based on deep learning. In this paper, we apply the concept of combining Transformer and CNN to the financial field, building on the traditional CNN-Transformer model’s capacity to effectively process local features, perform parallel processing, and handle long-distance dependencies. To enhance the model’s ability to capture financial data over extended periods and address the challenge of high-dimensional financial data, we propose a novel hybrid model, TCN-DilateFormer. This integration improves the accuracy of corporate credit risk assessment. The empirical study demonstrates that the model exhibits superior prediction accuracy compared to traditional machine learning assessment models, thereby offering a novel and efficacious tool for corporate credit risk assessment.https://doi.org/10.1038/s41598-025-86371-7Feature captureLong-range dependenciesCredit riskDeep learningMachine learning |
| spellingShingle | Chuanhe Shen Junzhe Wu Research on credit risk of listed companies: a hybrid model based on TCN and DilateFormer Scientific Reports Feature capture Long-range dependencies Credit risk Deep learning Machine learning |
| title | Research on credit risk of listed companies: a hybrid model based on TCN and DilateFormer |
| title_full | Research on credit risk of listed companies: a hybrid model based on TCN and DilateFormer |
| title_fullStr | Research on credit risk of listed companies: a hybrid model based on TCN and DilateFormer |
| title_full_unstemmed | Research on credit risk of listed companies: a hybrid model based on TCN and DilateFormer |
| title_short | Research on credit risk of listed companies: a hybrid model based on TCN and DilateFormer |
| title_sort | research on credit risk of listed companies a hybrid model based on tcn and dilateformer |
| topic | Feature capture Long-range dependencies Credit risk Deep learning Machine learning |
| url | https://doi.org/10.1038/s41598-025-86371-7 |
| work_keys_str_mv | AT chuanheshen researchoncreditriskoflistedcompaniesahybridmodelbasedontcnanddilateformer AT junzhewu researchoncreditriskoflistedcompaniesahybridmodelbasedontcnanddilateformer |