ARTICLE

Volume 2,Issue 7

Cite this article
3
Download
27
Citations
70
Views
20 May 2026

基于函数型数据分析的债券违约预测评估

凯 王1
Show Less
1 合肥工业大学 数学学院, 中国
ASDS 2026 , 2(5), 69–77; https://doi.org/10.61369/ASDS.2026050013
© 2026 by the Author(s). Licensee Art and Technology, USA. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC BY-NC 4.0) ( https://creativecommons.org/licenses/by-nc/4.0/ )
Abstract

对债券进行风险评估时,由于传统信用模型所用的是发行主体的静态财务报表及外部评级结果,故传统方法存在指标更新频率低、分析维度单一的问题,影响了预测评估的时效性及精确度。本文从函数型数据分析(FDA)的角度,结合债券利率等特征信息,用多种机器学习算法对债券违约进行了系统的预测评估。所得结果表明,具有函数型特征的债券风险评估模型在各评价指标上均有明显改进。

Keywords
债券违约
FDA
机器学习
利率特征
信用风险
References

[1] 祝小全, 梁洛铭, 陈卓. 中国债券市场风险、定价研究进展与服务实体经济的初步实践[J]. 中国科学基金, 2025, 39(02): 329-344.
[2] Chen T, Guestrin C. XGBoost: A scalable tree boosting system[C]//KDD. 2016: 785-794.
[3] Zhou L. A survey on machine learning models for credit scoring[J]. WIREs Data Mining Knowl Discov, 2013, 3(3): 191-203.
[4] 王玉龙, 周榴, 张涤霏. 企业债务违约风险预测—— 基于机器学习的视角[J]. 财政科学, 2022(6): 62-74.
[5] Chopra V, Bhilare P. Gradient boosting for credit risk prediction[J]. International Journal of Computer Applications, 2018, 182(20): 7-11.
[6] Sebastian H. Goldmann, Marcos R. Machado, Joerg R. Osterrieder. Advancing credit risk assessment in the retail banking industry: A hybrid approach using time series and supervised learning models[J]. Data & Knowledge Engineering, 2025, 160: 102490.
[7] 胡蝶. 基于随机森林的债券违约分析[J]. 当代经济, 2018(3): 28-30.
[8] 邓晴元. 基于 XGBoost 算法的债券违约风险预测研究[J]. 投资与创业, 2023, 34(2): 1-3.
[9] Tran T T, Tsai P H, Wilson L L. Combining genetic algorithm and deep learning for bankruptcy prediction[C]//ICDM. 2017: 617-624.
[10] Gu J, Qian X, Zheng H, et al. Machine learning for credit risk prediction: A macro–micro integrated approach[J]. Journal of Financial Stability, 2020, 49: 100708.
[11] Ramsay J O. When the data are functions[J]. Psychometrika, 1982, 47(4): 379-396.
[12] Ramsay J O, Dalzell C J. Some tools for functional data analysis[J]. Journal of the Royal Statistical Society: Series B, 1991, 53(3): 539-572.
[13] 王丙参, 魏艳华, 张贝贝. 函数型数据聚类算法的评价与比较[J]. 统计与决策, 2021, 37(16): 38-42.
[14] 魏艳华, 马立平, 王丙参. 基于函数型数据的中国人口变化趋势及地区差异研究[J]. 统计与决策, 2022, 38(8): 82-86.
[15] 王华强, 刘黎明. 基于函数型数据的利率与物价关系研究[J]. 数理统计与管理, 2024, 43(3): 452-464.
[16] Z. Tao, M. Wang, J. Liu, et al. A functional data analysis framework incorporating derivative information and mixed-frequency data for predictive modeling of crude oil price[J]. IEEE Transactions on Industrial Informatics, 2025, 21(4): 3226-3235.
[17] Kokoszka P. Introduction to functional data analysis[M]. CRC Press, 2017.
[18] Joaquín Sancho Val, Carlos Cajal Hernando, Lourdes Martínez de Baños. Functional data analysis of air quality time series in Madrid Using FPCA and splines[J]. Atmospheric Environment, 2026, 367: 121741.
[19] S. Nian, W. Kang, D. Wang. A general approach for health index-based remaining useful life prediction using functional principal component analysis[C]. 2024 Global Reliability and Prognostics and Health Management Conference, 2024.
[20] Breiman L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32.
[21] 姜高霞, 王文剑. 经济周期波动的函数型时序分解方法—— 基于CPI 的实证分析[J]. 统计与信息论坛,2014,29(03):22-28.
[22] 严明义, 杜鹏. 中国消费价格指数季节变动的函数性数据分析[J]. 统计与信息论坛, 2010, 25(08): 100-106.
[23] Chen H, Reiss PT, Tarpey T. Optimally weighted L2 distance for functional data[J]. Biometrics. 2014, 70(3): 516-525.
[24] 严明义. 函数性数据的分析方法与经济应用[M]. 中国财政经济出版社, 2014.

Share
Back to top