{"title":"金融危机预警系统:时间卷积网络方法","authors":"Shun Chen, Yi Huang, Lei Ge","doi":"10.3846/tede.2024.20555","DOIUrl":null,"url":null,"abstract":"The widespread and substantial effect of the global financial crisis in history underlines the importance of forecasting financial crisis effectively. In this paper, we propose temporal convolutional network (TCN), which based on a convolutional neural network, to construct an early warning system for financial crises. The proposed TCN is compared with logit model and other deep learning models. The Shapley value decomposition is calculated for the interpretability of the early warning system. Experimental results show that the proposed TCN outperforms other models, and the stock price and the real GDP growth have the largest contributions in the crises prediction.","PeriodicalId":51460,"journal":{"name":"Technological and Economic Development of Economy","volume":null,"pages":null},"PeriodicalIF":4.8000,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"AN EARLY WARNING SYSTEM FOR FINANCIAL CRISES: A TEMPORAL CONVOLUTIONAL NETWORK APPROACH\",\"authors\":\"Shun Chen, Yi Huang, Lei Ge\",\"doi\":\"10.3846/tede.2024.20555\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The widespread and substantial effect of the global financial crisis in history underlines the importance of forecasting financial crisis effectively. In this paper, we propose temporal convolutional network (TCN), which based on a convolutional neural network, to construct an early warning system for financial crises. The proposed TCN is compared with logit model and other deep learning models. The Shapley value decomposition is calculated for the interpretability of the early warning system. Experimental results show that the proposed TCN outperforms other models, and the stock price and the real GDP growth have the largest contributions in the crises prediction.\",\"PeriodicalId\":51460,\"journal\":{\"name\":\"Technological and Economic Development of Economy\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.8000,\"publicationDate\":\"2024-03-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Technological and Economic Development of Economy\",\"FirstCategoryId\":\"96\",\"ListUrlMain\":\"https://doi.org/10.3846/tede.2024.20555\",\"RegionNum\":2,\"RegionCategory\":\"经济学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ECONOMICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Technological and Economic Development of Economy","FirstCategoryId":"96","ListUrlMain":"https://doi.org/10.3846/tede.2024.20555","RegionNum":2,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ECONOMICS","Score":null,"Total":0}
引用次数: 0
摘要
全球金融危机在历史上造成的广泛而巨大的影响凸显了有效预测金融危机的重要性。本文提出了基于卷积神经网络的时序卷积网络(TCN)来构建金融危机预警系统。本文将时序卷积网络与 logit 模型和其他深度学习模型进行了比较。为了提高预警系统的可解释性,计算了 Shapley 值分解。实验结果表明,所提出的 TCN 优于其他模型,其中股票价格和实际 GDP 增长对危机预测的贡献最大。
AN EARLY WARNING SYSTEM FOR FINANCIAL CRISES: A TEMPORAL CONVOLUTIONAL NETWORK APPROACH
The widespread and substantial effect of the global financial crisis in history underlines the importance of forecasting financial crisis effectively. In this paper, we propose temporal convolutional network (TCN), which based on a convolutional neural network, to construct an early warning system for financial crises. The proposed TCN is compared with logit model and other deep learning models. The Shapley value decomposition is calculated for the interpretability of the early warning system. Experimental results show that the proposed TCN outperforms other models, and the stock price and the real GDP growth have the largest contributions in the crises prediction.
期刊介绍:
Technological and Economic Development of Economy is a refereed journal that publishes original research and review articles and book reviews. The Journal is designed for publishing articles in the following fields of research:
systems for sustainable development,
policy on sustainable development,
legislation on sustainable development,
strategies, approaches and methods for sustainable development,
visions and scenarios for the future,
education for sustainable development,
institutional change and sustainable development,
health care and sustainable development,
alternative economic paradigms for sustainable development,
partnership in the field of sustainable development,
industry and sustainable development,
sustainable development challenges to business and management,
technological changes and sustainable development,
social aspects of sustainability,
economic dimensions of sustainability,
political dimensions of sustainability,
innovations,
life cycle design and assessment,
ethics and sustainability,
sustainable design and material selection,
assessment of environmental impact,
ecology and sustainability,
application case studies,
best practices,
decision making theory,
models of operations research,
theory and practice of operations research,
statistics,
optimization,
simulation.
All papers to be published in Technological and Economic Development of Economy are peer reviewed by two appointed experts. The Journal is published quarterly, in March, June, September and December.