基于混合深度学习模型的上市公司绿色信贷违约风险预测研究

摘要/Abstract

摘要： 近年来，绿色信贷在推动我国绿色金融体系构建和经济高质量发展中发挥着越来越重要的作用，然而，上市公司在绿色信贷活动中的违约行为将带来金融市场的信任危机以及影响“双碳”目标的实现。因此，如何精准识别和预测上市公司的绿色信贷违约风险已成为学界和业界共同关注的热点。基于此，首先，本文构建综合绿色信贷违约占比和主体信用评级的违约风险度量指标，并挖掘上市公司绿色信贷数据开展特征工程；其次，基于自编码机制，融合多种神经网络技术，设计AE-MA-CNN-LSTM混合深度学习模型对上市公司绿色信贷违约风险进行预测；最后，选取我国A股上市公司为样本进行实证分析。结果表明：本文提出的方法在多个评价指标方面取得了更好的预测效果，具有较高的召回率和AUC。本研究为识别和防控上市公司绿色信贷风险提供了新的视角，对政府和投资者及时掌握企业绿色信贷动态具有参考价值。

关键词: 绿色信贷, 违约风险预测, 混合深度学习, 自编码器

Abstract: In recent years, green credit has played an increasingly important role in promoting the construction of China’s green financial system and facilitating high-quality economic development. However, default activities of listed companies in green credit may pose a trust crisis in the financial market and hinder the achievement of the "dual carbon" goals. Therefore, accurately identifying and predicting the green credit default risk of listed companies has become a focus in both academia and the industry. To address this, this paper first constructs a comprehensive measure of default risk, by incorporating the proportion of green credit defaults and the credit ratings of entities. And we process feature engineering by excavating the characteristics of green credit data for listed companies. Subsequently, a hybrid deep learning model, named AE-MACNN-LSTM, is designed by incorporating an AutoEncoder mechanism and various neural networks to predict the green credit default risk of listed companies. Finally, an empirical test is conducted based on samples of A-share listed companies in China. The results indicate that the proposed method achieves significant improvements in multiple evaluation metrics, such as high recall rates and AUC values. This research provides a novel perspective for identifying and mitigating the green credit risk of listed companies, offering valuable insights for the government and investors to timely grasp the dynamics of corporate green credit.

Key words: green credit, default risk predict, hybrid deep learning, AutoEncoder

陈炜, 周全世, 陈振松, 姚银红. 基于混合深度学习模型的上市公司绿色信贷违约风险预测研究[J]. 管理评论, 2025, 37(9): 27-41.

Chen Wei, Zhou Quanshi, Chen Zhensong, Yao Yinhong. A Study on Predicting Green Credit Default Risk of Publicly Listed Companies through a Hybrid Deep Learning Model[J]. Management Review, 2025, 37(9): 27-41.

参考文献

[1] 王馨, 王营. 绿色信贷政策增进绿色创新研究[J]. 管理世界, 2021, 37(6):173-188 Wang X., Wang Y. Research on the Green Innovation Promoted by Green Credit Policies[J]. Journal of Management World, 2021, 37(6):173-188
[2] 李俊成, 彭俞超, 王文蔚. 绿色信贷政策能否促进绿色企业发展——基于风险承担的视角[J]. 金融研究, 2023, (3):112-130 Li J. C., Peng Y. C., Wang W. W. Can the Green Credit Policy Promote the Development of Green Enterprises from the Perspective of Risk-taking？[J]. Journal of Financial Research, 2023, (3):112-130
[3] 林宇, 吴庆贺, 李昊, 等. 基于Twin-SVR的公司违约风险预测研究[J]. 管理评论, 2019, 31(11):33-43 Lin Y., Wu Q. H., Li H., et al. Research on Corporate Default Risk Prediction Based on Twin-SVR[J]. Management Review, 2019, 31(11):33-43
[4] 陈荣达, 虞欢欢, 余乐安, 等. 混合泊松违约强度下信用资产组合风险度量[J]. 管理科学学报, 2018, 21(12):54-69 Chen R. D., Yu H. H., Yu L. A., et al. Portfolio Credit Risk Measurement Based on Mixed Poisson Default Intensity[J]. Journal of Management Sciences in China, 2018, 21(12):54-69
[5] 周颖, 张志鹏. 基于违约企业分布约束的上市公司信用等级划分模型[J]. 管理评论, 2023, 35(5):3-18 Zhou Y., Zhang Z. P. Listed Company Credit Rating Division Model Based on Defaulting Customer Distribution Constraint[J]. Management Review, 2023, 35(5):3-18
[6] Sun Y., Chai N., Dong Y., et al. Assessing and Predicting Small Industrial Enterprises’ Credit Ratings: A Fuzzy Decision-making Approach[J]. International Journal of Forecasting, 2022, 38(3):1158-1172
[7] 邢秉昆. 碳减排约束下中国工业企业信用评级[J]. 金融研究, 2022, (11):77-97 Xing B. K. Credit Rating of Chinese Industrial Enterprises under the Constraints of Carbon Emission Reduction[J]. Journal of Financial Research, 2022, (11):77-97
[8] Galil K., Hauptman A., Rosenboim R. L. Prediction of Corporate Credit Ratings with Machine Learning: Simple Interpretative Models[J]. Finance Research Letters, 2023, 58:104648
[9] Moscatelli M., Parlapiano F., Narizzano S., et al. Corporate Default Forecasting with Machine Learning[J]. Expert Systems with Applications, 2020, 161:113567
[10] Ma X., Sha J., Wang D., et al. Study on a Prediction of P2P Network Loan Default Based on the Machine Learning LightGBM and XGboost Algorithms According to Different High Dimensional Data Cleaning[J]. Electronic Commerce Research and Applications, 2018, 31:24-39
[11] 周颖, 苏小婷. 基于最优指标组合的企业信用风险预测[J]. 系统管理学报, 2021, 30(5):817-838 Zhou Y., Su X. T. Credit Risk Prediction of Company Based on Optimal Feature Set[J]. Journal of Systems & Management, 2021, 30(5):817-838
[12] 赵雪峰, 吴德林, 吴伟伟, 等. 基于多头注意力机制的BM-Linear信用贷款评估模型[J]. 系统管理学报, 2023, 32(1):118-129 Zhao X. F., Wu D. L., Wu W. W., et al. A BM-Linear Credit Loan Evaluation Model Based on Multi-head Attention[J]. Journal of Systems & Management, 2023, 32(1):118-129
[13] Qian H., Ma P., Gao S., et al. Soft Reordering One-dimensional Convolutional Neural Network for Credit Scoring[J]. Knowledge-Based Systems, 2023, 266:110414
[14] Reddy N. M., Sharada K. A., Pilli D., et al. CNN-Bidirectional LSTM Based Approach for Financial Fraud Detection and Prevention System[C] //2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS). IEEE, 2023
[15] 柏凤山, 迟国泰, 温武军. 基于LSTM和多头注意力机制的企业违约预测模型[J]. 管理工程学报, 2024, 38(3):213-226 Bai F. S., Chi G. T., Wen W. J. Enterprise Default Prediction Model Based on LSTM and Multi-head Attention[J]. Journal of Industrial Engineering and Engineering Management, 2024, 38(3):213-226
[16] Xiao J., Zhong Y., Jia Y., et al. A Novel Deep Ensemble Model for Imbalanced Credit Scoring in Internet Finance[J]. International Journal of Forecasting, 2024, 40(1):348-372
[17] Fanai H., Abbasimehr H. A Novel Combined Approach Based on Deep Autoencoder and Deep Classifiers for Credit Card Fraud Detection[J]. Expert Systems with Applications, 2023, 217:119562
[18] 杨子晖, 张平淼, 林师涵. 系统性风险与企业财务危机预警——基于前沿机器学习的新视角[J]. 金融研究, 2022, (8):152-170 Yang Z. H., Zhang P. M., Lin S. H. Systemic Risk and Corporate Financial Distress Forecasting from the New Perspective of Machine Learning[J]. Journal of Financial Research, 2022, (8):152-170
[19] 佟孟华, 邢秉昆, 赵作伦, 等. 基于FM模型的工业企业碳减排信用风险预警研究[J]. 数量经济技术经济研究, 2021, 38(2):147-165 Tong M. H., Xing B. K., Zhao Z. L., et al. Early Warning Research on Carbon Emission Reduction Credit Risk of Industrial Enterprises Based on FM Model[J]. The Journal of Quantitative & Technical Economics, 2021, 38(2):147-165
[20] 李靖宇, 郭湘媛, 谢启伟, 等. 基于随机森林融合的金融机构风险关联影响因素研究[J]. 系统工程理论与实践, 2024, 44(1):296-319 Li J. Y., Guo X. Y., Xie Q. W., et al. Influencing Factors of the Risk Correlation of Financial Institutions: Evidence from Random Forest Fusion[J]. Systems Engineering-Theory & Practice, 2024, 44(1):296-319
[21] Park H. J., Kim Y., Kim H. Y. Stock Market Forecasting Using a Multi-task Approach Integrating Long Short-term Memory and the Random Forest Framework[J]. Applied Soft Computing, 2022, 114:108106
[22] Das Gupta S. Point Biserial Correlation Coefficient and Its Generalization[J]. Psychometrika, 1960, 25(4):393-408
[23] 郭春娜, 晏发发, 陈宇游. 现代化经济体系下制造业资本配置效率的分解及差异性研究[J]. 数量经济技术经济研究, 2021, 38(9):62-79 Guo C. N., Yan F. F., Chen Y. Y. A Study on the Decomposition and Differentiation of Capital Allocation Efficiency of the Manufacturing Industry[J]. The Journal of Quantitative & Technical Economics, 2021, 38(9):62-79
[24] Abdoli M., Akbari M., Shahrabi J. Bagging Supervised Autoencoder Classifier for Credit Scoring[J]. Expert Systems with Applications, 2023, 213:118991
[25] 曾宇容, 吴彬溶, 王林, 等. 基于多源异构数据的玉米期货价格可解释性预测[J]. 管理评论, 2023, 35(12):40-52 Zeng Y. R., Wu B. R., Wang L., et al. Interpretable Corn Futures Price Forecasting with Multivariate Heterogeneous Data[J]. Management Review, 2023, 35(12):40-52
[26] Shi F., Zhao C. Enhancing Financial Fraud Detection with Hierarchical Graph Attention Networks: A Study on Integrating Local and Extensive Structural Information[J]. Finance Research Letters, 2023, 58:104458
[27] 王刚, 陈红, 马敬玲, 等. 基于多尺度1D-CNN和注意力机制的汇率多步预测研究[J]. 系统工程理论与实践, 2024, 44(6):1934-1949 Wang G., Chen H., Ma J. L., et al. Multi-step Forecasting of Exchange Rate Based on Multi-scale 1D-CNN and Attention Mechanisms[J]. Systems Engineering-Theory & Practice, 2024, 44(6):1934-1949
[28] 赵琪, 徐维军, 季昱丞, 等. 基于卷积神经网络的财务困境预测:公司财报的图像化[J]. 管理工程学报, 2025, 39(1):46-62 Zhao Q., Xu W. J., Ji Y. C., et al. Financial Distress Prediction Based on Convolutional Neural Networks: Imaged Firms’ Financial Reports[J]. Journal of Industrial Engineering and Engineering Management, 2025, 39(1):46-62
[29] Shen F., Zhao X., Kou G., et al. A New Deep Learning Ensemble Credit Risk Evaluation Model with an Improved Synthetic Minority Oversampling Technique[J]. Applied Soft Computing, 2021, 98:106852
[30] 刘伟龙, 张永, 杨兴雨. 基于LSTM预测信息的在线融资融券组合交易策略[J]. 系统工程理论与实践, 2024, 44(8):2493-2511 Liu W. L., Zhang Y., Yang X. Y. Online Margin Trading Strategy Based on LSTM Prediction Information[J]. Systems Engineering-Theory & Practice, 2024, 44(8):2493-2511
[31] Morales-Hernández A., Van Nieuwenhuyse I., Rojas Gonzalez S. A Survey on Multi-objective Hyperparameter Optimization Algorithms for Machine Learning[J]. Artificial Intelligence Review, 2023, 56(8):8043-8093