Early Warning of Bond Defaults in Wholesale and Retail Enterprises: An Integrated Random Forest–BP Neural Network Approach

Xiuwen Zhu

doi:10.54254/2754-1169/2025.27918

Advances in Economics, Management and Political SciencesOpen access

Early Warning of Bond Defaults in Wholesale and Retail Enterprises: An Integrated Random Forest–BP Neural Network Approach

Research Article

Open Access

Early Warning of Bond Defaults in Wholesale and Retail Enterprises: An Integrated Random Forest–BP Neural Network Approach

Xiuwen Zhu ^1*

¹ Shandong Technology and Business University

^*Corresponding author: 19861817406@163.com

Published on 14 October 2025

AEMPS Vol.227

ISSN (Print): 2754-1177

ISSN (Online): 2754-1169

ISBN (Print): 978-1-80590-309-3

ISBN (Online): 978-1-80590-310-9

Download Cover

Abstract

Aiming at the problem that traditional default early warning models have insufficient discriminative power and robustness under the scenario of strong correlation among high-dimensional indicators and unbalanced samples, this study proposes a serial fusion model integrating Random Forest (RF) and Back Propagation (BP) Neural Network. First, RF is used for feature selection: the minimum sufficient feature set is screened out based on the criterion of cumulative contribution ≥ 90%, which corresponds to the input layer nodes of the BP Neural Network. Subsequently, the BP Neural Network is applied to perform nonlinear fitting on the selected features. During the training phase, ADASYN (Adaptive Synthetic Sampling Approach) oversampling is only implemented on the training set to balance samples while preventing information leakage. The model is trained and evaluated using samples from the wholesale and retail industry, and its early warning effect is verified by predicting the default probability of Gome Electrical Appliances. The results show that the RF-BP model has strong early warning capability for small to medium-sized samples and can issue risk early warning signals in advance.

Keywords:

Random Forest (RF), Back Propagation (BP) Neural Network, feature selection, unbalanced samples, default early warning

View PDF

References

[1]. Li, Y. C., & Bao, X. J. (2020). Integration degree, macroeconomic fluctuations and corporate debt default. Modern Finance and Economics (Journal of Tianjin University of Finance and Economics), 40(08), 73-87. https: //doi.org/10.19559/j.cnki.12-1387.2020.08.006

[2]. Yang, J. Q., Lin, C. P., & Hu, T. (2022). Asset liquidity, government bailout intensity and corporate default risk. Systems Engineering-Theory & Practice, 42(09), 2333-2349.

[3]. Sun, L., & Sun, J. (2022). Analysis of influencing factors of listed companies' bond default: A study based on corporate financial leverage and diversified operation. Shanghai Finance, (11), 2-11. https: //doi.org/10.13910/j.cnki.shjr.2022.11.001

[4]. Dou, C., Yang, X., Liu, W., et al. (2022). Independent directors' macro perspective and corporate debt default. Accounting Research, (07), 58-74.

[5]. Qin, J. D., Deng, D., & Liu, J. W. (2023). No actual controller and corporate debt default risk. Shanghai Finance, (12), 3-18. https: //doi.org/10.13910/j.cnki.shjr.2023.12.001

[6]. Pan, Y. L., & Xu, A. M. (2023). Can employee stock ownership plans inhibit corporate debt default risk? Journal of Hangzhou Dianzi University (Social Sciences Edition), 19(02), 25-33+41. https: //doi.org/10.13954/j.cnki.hduss.2023.02.004

[7]. Wang, Y. L., Zhou, L., & Zhang, D. F. (2022). Corporate debt default risk prediction: From the perspective of machine learning. Fiscal Science, (06), 62-74. https: //doi.org/10.19477/j.cnki.10-1368/f.2022.06.010

[8]. Jiang, F. W., Lin, Y. H., & Ma, T. (2023). Corporate bond default risk under the background of "breaking rigid payment": Machine learning early warning and economic mechanism exploration. Journal of Financial Research, (10), 85-103.

[9]. Hu, Y. L. (2024). Early warning and prevention strategies of bond default risk for commercial circulation enterprises: Analysis based on support vector machine algorithm. Journal of Commercial Economics, (18), 164-167.

[10]. Li, Y., Wang, Z., & Ma, F. (2023). Bond Default Prediction with Temporal Graph Convolutional Neural Network and Weakly Supervised Learning. Procedia Computer Science, 221, 1376-1385.

[11]. Gao, Y., Du, Y., & Zeng, S. (2023). Research on financial risk early warning of manufacturing enterprises based on BP neural network. Friends of Accounting, (01), 62-70.

[12]. Yang, G. J., Du, F., & Jia, X. L. (2022). Financial risk early warning model of BP neural network based on first and last quality factors. Statistics & Decision, 38(03), 166-171. https: //doi.org/10.13546/j.cnki.tjyjc.2022.03.031

[13]. Li, C. G., Jia, H. Y., Zhao, G. H., et al. (2023). Credit risk early warning of listed companies based on information disclosure text: Empirical evidence from management discussion and analysis in Chinese annual reports. Chinese Journal of Management Science, 31(02), 18-29. https: //doi.org/10.16381/j.cnki.issn1003-207x.2020.2263

References

[2]. Yang, J. Q., Lin, C. P., & Hu, T. (2022). Asset liquidity, government bailout intensity and corporate default risk. Systems Engineering-Theory & Practice, 42(09), 2333-2349.

[4]. Dou, C., Yang, X., Liu, W., et al. (2022). Independent directors' macro perspective and corporate debt default. Accounting Research, (07), 58-74.

[5]. Qin, J. D., Deng, D., & Liu, J. W. (2023). No actual controller and corporate debt default risk. Shanghai Finance, (12), 3-18. https: //doi.org/10.13910/j.cnki.shjr.2023.12.001

[10]. Li, Y., Wang, Z., & Ma, F. (2023). Bond Default Prediction with Temporal Graph Convolutional Neural Network and Weakly Supervised Learning. Procedia Computer Science, 221, 1376-1385.

[11]. Gao, Y., Du, Y., & Zeng, S. (2023). Research on financial risk early warning of manufacturing enterprises based on BP neural network. Friends of Accounting, (01), 62-70.

Cite this article

Zhu,X. (2025). Early Warning of Bond Defaults in Wholesale and Retail Enterprises: An Integrated Random Forest–BP Neural Network Approach. Advances in Economics, Management and Political Sciences,227,42-51.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

About volume

Volume title: Proceedings of the 9th International Conference on Economic Management and Green Development

ISBN: 978-1-80590-309-3(Print) / 978-1-80590-310-9(Online)

Editor: Florian Marcel Nuţă Nuţă, Xuezheng Qin

Conference website: https://2025.icemgd.org/

Conference date: 20 September 2025

Series: Advances in Economics, Management and Political Sciences

Volume number: Vol.227

ISSN: 2754-1169(Print) / 2754-1177(Online)

© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. Authors who publish this series agree to the following terms:

1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.

2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.

3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open access policy for details).