Predicting Bond Default Risk Based on the XGBoost Model
Main Article Content
Keywords
bond default, XGBoost, default prediction
Abstract
At present, China faces a large scale of bond defaults. To address the problems of low prediction accuracy and limited indicator systems in traditional models, this paper conducts research on bond default risk prediction based on the XGBoost model. This study selects 616 valid samples of credit bonds from entity industries in the Wind database from 2019 to 2024, and constructs a multi-dimensional indicator system covering bond characteristics, financial leverage, and other factors. After data cleaning and feature selection, the dataset is divided into training and test sets at a 7:3 ratio, and the XGBoost model is trained using 3-fold cross-validation. The results show that the sustainability of corporate profitability is the core influencing factor of default. The model achieves an AUC of 0.997 on the test set, with no severe overfitting, demonstrating excellent generalization ability and prediction accuracy. This provides methodological support for the prevention and control of bond default risk.
References
- [1] Wang, L. S. & Guo, S. J. (2025). Bond default prediction of listed companies based on Stacking ensemble. Modern Information Technology, 9(20), 171-177. https://doi.org/10.19850/j.cnki.2096-4706.2025.20.031.
- [2] Zhu, L., & Du, X. Q. (2025). The impact of green innovation on corporate bond default risk. Modern Finance, (12), 48-56+29.
- [3] Zhong, N. H., Hao, Y. T., & Liu, Y. Y. (2025). Research on early warning of real estate bond defaults based on unstructured text. Journal of Sun Yat-sen University (Social Science Edition), 65(04), 359-374. https://doi.org/10.13471/j.cnki.jsysusse.2025.04.030.
- [4] Gao, L. Y. (2025). Research on bond default prediction of listed companies based on LDA-XGBoost [Master's thesis, Dalian Jiaotong University]. https://doi.org/10.26990/d.cnki.gsltc.2025.000434.
- [5] Suganda, T. R., & Kim, J. (2023). An empirical study on the relationship between corporate social responsibility and default risk: Evidence in Korea. Sustainability, 15(4), Article 3644. https://doi.org/10.3390/su15043644.
- [6] Chen, R. (2025). Analysis of the causes of bond defaults in state-owned enterprises and research on improvement strategies. Business Manager, (06), 96-98.
- [7] Li, C., & Qu, Y. H. (2025). Research on the relationship between high-quality corporate development and bond default risk. Friends of Accounting, (20), 22-31.
- [8] Yu, Y. P. (2024). Research on bond default risk prediction model based on multi-source heterogeneous data [Master's thesis, Sichuan University]. https://kns.cnki.net/kcms2/article/abstract?v=OGEEvuKkrhYhOLT1kNnqxIBGlVdhkKYN4yn982zLSC5bohlBvUswyLG5VTVFLpy8DNMKowzr_cb4oZfSQHPJ-MrSoDMK8wO0h7IfY9MiBPNT8LfcLe-4BQbH2JMp8Dvl7Ow5o-ehs2Qx0NMfu86wnnqmmeLZTGSVkTZz-EuK1hg51kny_5NXGQ==&uniplatform=NZKPT&language=CHS.
- [9] Li, W., Ding, S., Chen, Y., & Yang, S. (2018). Heterogeneous ensemble for default prediction of peer-to-peer lending in China. IEEE Access. Advance online publication. https://doi.org/10.1109/ACCESS.2018.2810864
- [10] Xiao, Y. L., & Xiang, Y. T. (2021). Early warning of corporate bond default risk: Based on the GWO-XGBoost method. Shanghai Finance, (10), 44-54. https://doi.org/10.13910/j.cnki.shjr.2021.10.005
Article Sidebar
This work is licensed under a Creative Commons Attribution 4.0 International License.