94% of researchers rate our articles as excellent or good
Learn more about the work of our research integrity team to safeguard the quality of each article we publish.
Find out more
ORIGINAL RESEARCH article
Front. Phys.
Sec. Social Physics
Volume 13 - 2025 | doi: 10.3389/fphy.2025.1559283
This article is part of the Research Topic Finance and Production Complex Systems View all 9 articles
Research on Characterization and Prediction of Bond Risk Factors Based on Machine Learning: Evidence from the China
Provisionally accepted
Yaowen Zhang 
Wei Cui *- China University of Geosciences, Beijing, China
The default scale of China's credit bonds has been increasing. Defaults on credit bonds not only increase the cost of corporate finance, but also affect the efficiency of debt issuance and even cause the spread of risk among financial markets. It is essential to accurately identify the mechanisms of bond default risk and the associated risks of default. This paper focuses on corporate credit bonds as research subject, analyzing the causal relationship between macroeconomic indicators and bond defaults, employing association rule mining to elucidate the macro distribution of bond risks. Based on the bond credit related factors, we establish a bond default identification system, and the default prediction is made based on the combination learning algorithm. The results show the macro-monetary index is the Granger cause of bond default, the industry and main attribute of the issuing subject are the strong correlation factors. The combinatorial learning algorithm can obtain the strong correlation properties of defaulted bonds from the micro level, which can further verify the causal relationship confirmed. The research proves it's reasonable to select macro indicators for bond default prediction. Analyzing from both macro and micro perspectives aids in comprehensively understanding bond default risks.
Keywords: Chinese bond market, Bond credit default prediction, Macro factors and default causality, Combinatorial machine learning, Granger causality test, association rule mining
Received: 12 Jan 2025; Accepted: 13 Mar 2025.
Copyright: © 2025 Zhang and Cui. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Wei Cui, China University of Geosciences, Beijing, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.