Author(s)

Yunpeng Zhao ¹

Affiliation(s)

¹ Treasury Department, Bank of China, New York, NY 10018, USA

Corresponding Author

Yunpeng Zhao

ABSTRACT

Against the backdrop of increasingly severe credit bond default risks in China, how to accurately identify and efficiently warn of corporate bond default risks has become a major focus of academic and practical fields. This study aims to overcome the shortcomings of traditional default risk warning models in terms of predictive ability, hyperparameter adjustment, and model interpretability. We have constructed a novel corporate bond default risk warning model, LightGBM-NSGA-II-SHAP, by organically integrating LightGBM, NSGA-II, and SHAP algorithms. Through empirical testing, the warning accuracy of this model exceeds 85%, and its performance is significantly better than traditional methods. In addition, the application of SHAP algorithm enables the visualization of the impact of warning features, and the results show that features such as coupon rate, net profit margin of fixed assets, total issuance amount, and accounts receivable turnover rate are crucial for identifying bond defaults.

KEYWORDS

Bond Default; Risk Identification; Machine Learning

CITE THIS PAPER

Yunpeng Zhao, Research on Interpretable Machine Learning Models for Identifying Corporate Bond Default Risk. Population, Resources & Environmental Economics (2025) Vol. 6: 38-45. DOI: http://dx.doi.org/10.23977/pree.2025.060106.

REFERENCES

[1] Liu P, Li Y. Comparative analysis of machine learning models for bond default forecasting based on financial data of Chinese listed companies [J]. BCP Business & Management, 2022, 34: 1151-1158.
[2] Huan Z. On the effectiveness of graph statistics of shareholder relation network in predicting bond default risk [J]. Journal of Control Science and Engineering, 2022, 2022: 8401354.
[3] Lei S, Liang X, Wang X, et al. A short-term net load forecasting method based on two-stage feature selection and LightGBM with hyperparameter auto-tuning[C]. IEEE/IAS 59th Industrial and Commercial Power Systems Technical Conference, 2023: 1-6.
[4] Tang M, Zeng W, Zhao R. Corporate credit risk rating model based on financial big data [J]. BCP Business & Management, 2023, 48: 33-42 
[5] Chen, H., Ma, K., & Shen, J. Interpretable Machine Learning Facilitates Disease Prognosis: Applicationson COVID-19 and Onward [J]. International Journal of Computer Science and Information Technology, 2024, 3(3), 428-436. 
[6] Chen, H., Yang, Y., & Shao, C. Multi-task learning for data-efficient spatiotemporal modeling of tool surface progression in ultrasonic metal welding [J]. Journal of Manufacturing Systems, 2021, 58, 306-315.

Sponsors, Associates, and Links

---

• Information Systems and Economics
  
  
• Accounting, Auditing and Finance
  
  
• Industrial Engineering and Innovation Management
  
  
• Tourism Management and Technology Economy
  
  
• Journal of Computational and Financial Econometrics
  
  
• Financial Engineering and Risk Management
  
  
• Accounting and Corporate Management
  
  
• Social Security and Administration Management
  
  
• Statistics & Quantitative Economics
  
  
• Agricultural & Forestry Economics and Management
  
  
• Social Medicine and Health Management
  
  
• Land Resource Management
  
  
• Information, Library and Archival Science
  
  
• Journal of Human Resource Development
  
  
• Manufacturing and Service Operations Management
  
  
• Operational Research and Cybernetics