Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (10): 3223-3231.DOI: 10.11772/j.issn.1001-9081.2023101387

• Frontier and comprehensive applications • Previous Articles     Next Articles

Industrial chain risk assessment and early warning model combining hierarchical graph neural network and long short-term memory

Xiaoyu HUA1, Dongfen LI1, You FU1, Kejun BI2, Shi YING3, Ruijin WANG4()   

  1. 1.College of Computer Science and Cyber Security (Pilot Software College),Chengdu University of Technology,Chengdu Sichuan 610059,China
    2.College of Computer Science,Sichuan University,Chengdu Sichuan 610065,China
    3.School of Computer Science,Wuhan University,Wuhan Hubei 430072,China
    4.School of Information and Software Engineering,University of Electronic Science and Technology of China,Chengdu Sichuan 610054,China
  • Received:2023-10-17 Revised:2024-01-29 Accepted:2024-02-05 Online:2024-10-15 Published:2024-10-10
  • Contact: Ruijin WANG
  • About author:HUA Xiaoyu, born in 1999, M. S. candidate. His research interests include graph neural network, industrial chain risk assessment and early warning.
    LI Dongfen, born in 1979, Ph. D., associate professor. Her research interests include artificial intelligence, risk assessment and early warning, quantum cryptographic communication.
    FU You, born in 1999, M. S. candidate. His research interests include industrial chain risk assessment and early warning, quantum cryptographic communication.
    BI Kejun, born in 1982, M. S., senior engineer. His research interests include industrial Internet, artificial intelligence, construction of industrial chain knowledge graph.
    YING Shi, born in 1965, Ph. D., professor. His research interests include efficient processing and intelligent analysis of big data, machine learning, artificial intelligence, construction of industrial chain knowledge graph.
  • Supported by:
    National Key R&D Program of China(2022YFB3304300)

结合层次图神经网络与长短期记忆的产业链风险评估预警模型

花晓雨1, 李冬芬1, 付优1, 毕可骏2, 应时3, 王瑞锦4()   

  1. 1.成都理工大学 计算机与网络安全学院(示范性软件学院),成都 610059
    2.四川大学 计算机学院,成都 610065
    3.武汉大学 计算机学院,武汉 430072
    4.电子科技大学 信息与软件工程学院,成都 610054
  • 通讯作者: 王瑞锦
  • 作者简介:花晓雨(1999—),男,河南信阳人,硕士研究生,CCF会员,主要研究方向:图神经网络、产业链风险评估预警
    李冬芬(1979—),女,青海海东人,副教授,博士,CCF会员,主要研究方向:人工智能、风险评估与预警、量子密码通信
    付优(1999—),男,四川成都人,硕士研究生,主要研究方向:产业链风险评估预警、量子密码通信
    毕可骏(1982—),男,四川德阳人,高级工程师,硕士,主要研究方向:工业互联网、人工智能、产业链知识图谱构建
    应时(1965—),男,湖北武汉人,教授,博士,CCF会员,主要研究方向:大数据高效处理与智能分析、机器学习、人工智能、产业链知识图谱构建
    王瑞锦(1980—),男,甘肃天水人,副教授,博士,CCF会员,主要研究方向:边缘计算、人工智能、信息加密、产业链风险评估 ruijinwang@uestc.edu.cn
  • 基金资助:
    国家重点研发计划项目(2022YFB3304300)

Abstract:

Industrial chain risk assessment and early warning are essential measures to effectively protect the interests of upstream and downstream companies in the industrial chain and mitigate company risks. However, existing methods often need to pay more attention to the propagation effects between upstream and downstream companies in the industrial chain and the opacity of company information, resulting in inaccurate risk assessment of companies and the failure to perceive risks in advance for early warning. To address the above problems, the Hierarchical Graph Neural Network (HiGNN), an industrial chain risk assessment and early warning model that combined Hierarchical Graph (HG) neural network and Long Short-Term Memory (LSTM), was proposed. Firstly, an “industrial chain-investment” HG was constructed based on the relationships between upstream and downstream companies and investment activities. Then, a financial feature extraction module was utilized to extract features from multi-quarter financial data of companies, while an investment feature extraction module was utilized to extract features from the investment relationship graph. Finally, an attention mechanism was employed to integrate the financial features with the investment features, enabling risk classification of company nodes through graph representation learning methods. The experimental results on a real integrated circuit manufacturing dataset showed that compared with the Graph ATtention network (GAT) model and the Recurrent Neural Network (RNN) model, the accuracy of the proposed model increased by 14.87% and 22.10%, and the F1-score increased by 12.63% and 16.67% with the 60% training ratio. The proposed model can effectively capture the contagion effect in the industrial chain and improve risk identification capability, which is superior to traditional machine learning methods and graph neural network methods.

Key words: industrial chain risk assessment, Hierarchical Graph (HG) neural network, Long Short-Term Memory (LSTM) network, financial feature extraction, investment feature extraction

摘要:

产业链风险评估预警是有效保护产业链上下游公司利益和减轻公司风险的重要措施。然而,现有方法由于忽视了产业链上下游公司之间的传播效应和公司信息的不透明性,无法准确评估公司风险,且忽略了动态财务数据对产业链的影响,无法提前感知风险,进行风险预警。针对以上问题,提出一种结合层次图(HG)神经网络与长短期记忆(LSTM)的产业链风险评估预警模型(HiGNN)。首先,利用产业链上下游关系和投融资关系构建“产业链-投资”HG;其次,利用财务特征提取模块提取公司多季度财务数据的特征;再次,利用投资特征提取模块提取投资关系图特征;最后,利用注意力机制融合财务特征和投资特征,通过图表示学习方法对公司节点进行风险分类。在真实的集成电路制造业数据集上的实验结果表明,与图注意力网络(GAT)模型、循环神经网络(RNN)模型相比,当训练比率为60%时,所提模型的准确率分别提升了14.87%、22.10%,F1值提升了12.63%、16.67%。所提模型能够有效捕捉产业链中的传染效应,提高风险识别能力,优于传统的机器学习方法和图神经网络方法。

关键词: 产业链风险评估, 层次图神经网络, 长短期记忆网络, 财务特征提取, 投资特征提取

CLC Number: