Credit Risk Prediction Model for Listed Companies Based on CNN-LSTM and Attention Mechanism

被引:9
|
作者
Li, Jingyuan [1 ]
Xu, Caosen [1 ]
Feng, Bing [1 ]
Zhao, Hanyu [2 ]
机构
[1] Wuhan Inst Technol, Sch Management, Wuhan 430205, Peoples R China
[2] Beijing Acad Artificial Intelligence, Beijing 100084, Peoples R China
基金
国家重点研发计划;
关键词
CNN; attentional mechanisms; LSTM; credit risk;
D O I
10.3390/electronics12071643
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The financial market has been developing rapidly in recent years, and the issue of credit risk concerning listed companies has become increasingly prominent. Therefore, predicting the credit risk of listed companies is an urgent concern for banks, regulators and investors. The commonly used models are the Z-score, Logit (logistic regression model), the kernel-based virtual machine (KVM) and neural network models. However, the results achieved could be more satisfactory. This paper proposes a credit-risk-prediction model for listed companies based on a CNN-LSTM and an attention mechanism, Our approach is based on the benefits of the long short-term memory network (LSTM) model for long-term time-series prediction combined with a convolutional neural network (CNN) model. Furthermore, the advantages of being integrated into a CNN-LSTM model include reducing the complexity of the data, improving the calculation speed and training speed of the model and solving the possible lack of historical data in the long-term sequence prediction of the LSTM model, resulting in prediction accuracy. To reduce problems, we introduced an attention mechanism to assign weights independently and optimize the model. The results show that our model has distinct advantages compared with other CNNs, LSTMs, CNN-LSTMs and other models. The research on the credit-risk prediction of the listing formula has significant meaning.
引用
收藏
页数:18
相关论文
共 50 条
  • [31] A CNN-LSTM Stock Prediction Model Based on Genetic Algorithm Optimization
    Baek, Heon
    ASIA-PACIFIC FINANCIAL MARKETS, 2024, 31 (02) : 205 - 220
  • [32] Gun Life Prediction Model Based on Bayesian Optimization CNN-LSTM
    Wang Min
    Lu Xikun
    Zhou Yi-di
    INTEGRATED FERROELECTRICS, 2022, 228 (01) : 107 - 116
  • [33] Shape Coordinate Prediction of Multi-Core Optical Fiber Based on CNN-LSTM Network and Attention Mechanism
    Wang, Jianjian
    Tang, Rui
    ACTA OPTICA SINICA, 2025, 45 (01)
  • [34] Research on Parking Space Detection and Prediction Model Based on CNN-LSTM
    Xu, Zhuye
    Tang, Xiao
    Ma, Changxi
    Zhang, Renshuai
    IEEE ACCESS, 2024, 12 : 30085 - 30100
  • [35] Temporal Transfer Learning for Ozone Prediction based on CNN-LSTM Model
    Deng, Tuo
    Manders, Astrid
    Segers, Arjo
    Bai, Yanqin
    Lin, Hai Xiang
    ICAART: PROCEEDINGS OF THE 13TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE - VOL 2, 2021, : 1005 - 1012
  • [36] Lane Change Intention Prediction of CNN-LSTM Based on Multi-head Attention
    Gao K.
    Li X.
    Hu L.
    Chen B.
    Du R.
    Jixie Gongcheng Xuebao/Journal of Mechanical Engineering, 2022, 58 (22): : 369 - 378
  • [37] CNN-LSTM Coupled Model for Prediction of Waterworks Operation
    Cao, Kerang
    Kim, Hangyung
    Hwang, Chulhyun
    Jung, Hoekyung
    JOURNAL OF INFORMATION PROCESSING SYSTEMS, 2018, 14 (06): : 1508 - 1520
  • [38] Vehicle Road Grade Prediction Based on CNN-LSTM
    Qin, Tang
    Yao, Zhuoxiao
    Fan, Honggang
    Xia, Ran
    Chen, Tao
    IFAC PAPERSONLINE, 2023, 56 (02): : 3066 - 3071
  • [39] Massive MIMO CSI reconstruction using CNN-LSTM and attention mechanism
    Zhang, Zufan
    Zheng, Yue
    Gan, Chenquan
    Zhu, Qingyi
    IET COMMUNICATIONS, 2020, 14 (18) : 3089 - 3094
  • [40] CNN-LSTM based incremental attention mechanism enabled phase-space reconstruction for chaotic time series prediction
    Lu X.-Q.
    Tian J.
    Liao Q.
    Xu Z.-W.
    Gan L.
    Journal of Electronic Science and Technology, 2024, 22 (02)