A Hybrid XGBoost-MLP Model for Credit Risk Assessment on Digital Supply Chain Finance
Supply Chain Finance (SCF) has gradually taken on digital characteristics with the rapid development of electronic information technology. Business audit information has become more abundant and complex, which has increased the efficiency and increased the potential risk of commercial banks, with cr...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Forecasting |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2571-9394/4/1/11 |
| _version_ | 1827649055015043072 |
|---|---|
| author | Yixuan Li Charalampos Stasinakis Wee Meng Yeo |
| author_facet | Yixuan Li Charalampos Stasinakis Wee Meng Yeo |
| author_sort | Yixuan Li |
| collection | DOAJ |
| description | Supply Chain Finance (SCF) has gradually taken on digital characteristics with the rapid development of electronic information technology. Business audit information has become more abundant and complex, which has increased the efficiency and increased the potential risk of commercial banks, with credit risk being the biggest risk they face. Therefore, credit risk assessment based on the application of digital SCF is of great importance to commercial banks’ financial decisions. This paper uses a hybrid Extreme Gradient Boosting Multi-Layer Perceptron (XGBoost-MLP) model to assess the credit risk of Digital SCF (DSCF). In this paper, 1357 observations from 85 Chinese-listed SMEs over the period 2016–2019 are selected as the empirical sample, and the important features of credit risk assessment in DSCF are automatically selected through the feature selection of the XGBoost model in the first stage, then followed by credit risk assessment through the MLP in the second stage. Based on the empirical results, we find that the XGBoost-MLP model has good performance in credit risk assessment, where XGBoost feature selection is important for the credit risk assessment model. From the perspective of DSCF, the results show that the inclusion of digital features improves the accuracy of credit risk assessment in SCF. |
| first_indexed | 2024-03-09T19:50:46Z |
| format | Article |
| id | doaj.art-c9ad6ee376f4406395b0746f4046fe6a |
| institution | Directory Open Access Journal |
| issn | 2571-9394 |
| language | English |
| last_indexed | 2024-03-09T19:50:46Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Forecasting |
| spelling | doaj.art-c9ad6ee376f4406395b0746f4046fe6a2023-11-24T01:11:47ZengMDPI AGForecasting2571-93942022-01-014118420710.3390/forecast4010011A Hybrid XGBoost-MLP Model for Credit Risk Assessment on Digital Supply Chain FinanceYixuan Li0Charalampos Stasinakis1Wee Meng Yeo2Department of Accounting and Finance, Adam Smith Business School, University of Glasgow, Room 302, 11 Southpark Terrace, Glasgow G12 8LG, UKDepartment of Accounting and Finance, Adam Smith Business School, University of Glasgow, University Avenue, West Quadrangle, Gilbert Scott Building, Glasgow G12 8QQ, UKDepartment of Management, Adam Smith Business School, University of Glasgow, University Avenue, West Quadrangle, Gilbert Scott Building, Glasgow G12 8QQ, UKSupply Chain Finance (SCF) has gradually taken on digital characteristics with the rapid development of electronic information technology. Business audit information has become more abundant and complex, which has increased the efficiency and increased the potential risk of commercial banks, with credit risk being the biggest risk they face. Therefore, credit risk assessment based on the application of digital SCF is of great importance to commercial banks’ financial decisions. This paper uses a hybrid Extreme Gradient Boosting Multi-Layer Perceptron (XGBoost-MLP) model to assess the credit risk of Digital SCF (DSCF). In this paper, 1357 observations from 85 Chinese-listed SMEs over the period 2016–2019 are selected as the empirical sample, and the important features of credit risk assessment in DSCF are automatically selected through the feature selection of the XGBoost model in the first stage, then followed by credit risk assessment through the MLP in the second stage. Based on the empirical results, we find that the XGBoost-MLP model has good performance in credit risk assessment, where XGBoost feature selection is important for the credit risk assessment model. From the perspective of DSCF, the results show that the inclusion of digital features improves the accuracy of credit risk assessment in SCF.https://www.mdpi.com/2571-9394/4/1/11supply chain financecredit risk assessmentmachine learningXGBoost-MLP |
| spellingShingle | Yixuan Li Charalampos Stasinakis Wee Meng Yeo A Hybrid XGBoost-MLP Model for Credit Risk Assessment on Digital Supply Chain Finance Forecasting supply chain finance credit risk assessment machine learning XGBoost-MLP |
| title | A Hybrid XGBoost-MLP Model for Credit Risk Assessment on Digital Supply Chain Finance |
| title_full | A Hybrid XGBoost-MLP Model for Credit Risk Assessment on Digital Supply Chain Finance |
| title_fullStr | A Hybrid XGBoost-MLP Model for Credit Risk Assessment on Digital Supply Chain Finance |
| title_full_unstemmed | A Hybrid XGBoost-MLP Model for Credit Risk Assessment on Digital Supply Chain Finance |
| title_short | A Hybrid XGBoost-MLP Model for Credit Risk Assessment on Digital Supply Chain Finance |
| title_sort | hybrid xgboost mlp model for credit risk assessment on digital supply chain finance |
| topic | supply chain finance credit risk assessment machine learning XGBoost-MLP |
| url | https://www.mdpi.com/2571-9394/4/1/11 |
| work_keys_str_mv | AT yixuanli ahybridxgboostmlpmodelforcreditriskassessmentondigitalsupplychainfinance AT charalamposstasinakis ahybridxgboostmlpmodelforcreditriskassessmentondigitalsupplychainfinance AT weemengyeo ahybridxgboostmlpmodelforcreditriskassessmentondigitalsupplychainfinance AT yixuanli hybridxgboostmlpmodelforcreditriskassessmentondigitalsupplychainfinance AT charalamposstasinakis hybridxgboostmlpmodelforcreditriskassessmentondigitalsupplychainfinance AT weemengyeo hybridxgboostmlpmodelforcreditriskassessmentondigitalsupplychainfinance |