Learning Dynamic Dependencies With Graph Evolution Recurrent Unit for Stock Predictions

doi:10.1109/TSMC.2023.3284840

CORC > 自动化研究所 > 中国科学院自动化研究所 > 舆论大数据科学与技术应用联合实验室

	Learning Dynamic Dependencies With Graph Evolution Recurrent Unit for Stock Predictions
	Tian, Hu 1,2; Zhang, Xingwei 1,2; Zheng, Xiaolong 1,2; Zeng, Daniel Dajun 1,2
刊名	IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
	2023-07-10
页码	13
关键词	Gated recurrent unit graph representation learning learning dynamic dependencies stock prediction system
ISSN号	2168-2216
DOI	10.1109/TSMC.2023.3284840
通讯作者	Zheng, Xiaolong(xiaolong.zheng@ia.ac.cn)
英文摘要	Investment decisions and risk management require understanding the time-varying dependencies between stocks. Graph-based learning systems have emerged as a promising approach for predicting stock prices by leveraging interfirm relationships. However, existing methods rely on a static stock graph predefined from finance domain knowledge and large-scale data engineering, which overlooks the dynamic dependencies between stocks. In this article, we present a novel framework called graph evolution recurrent unit (GERU), which uses a dynamic graph neural network to automatically learn the evolving dependencies from historical stock features, leading to better predictions. Our approach consists of three parts: first, we develop an adaptive dynamic graph learning (ADGL) module to learn latent dynamic dependencies from stock time series. Second, we propose a clustered ADGL (clu-ADGL) to handle large-scale time series by reducing time and memory complexity. Third, we combine the ADGL/clu-ADGL with a graph-gated recurrent unit to model the temporal evolutions of stock networks. Extensive experiments on real-world datasets show that our proposed methods outperform existing methods in predicting stock movements, capturing meaningful dynamic dependencies and temporal evolution patterns from the financial market, and achieving outstanding profitability in portfolio construction.
资助项目	Ministry of Science and Technology of China[2020AAA0108401] ; Natural Science Foundation of China[72225011] ; Natural Science Foundation of China[72293575]
WOS关键词	NETWORK
WOS研究方向	Automation & Control Systems ; Computer Science
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001030654200001
资助机构	Ministry of Science and Technology of China ; Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53777]
专题	舆论大数据科学与技术应用联合实验室
通讯作者	Zheng, Xiaolong
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Tian, Hu,Zhang, Xingwei,Zheng, Xiaolong,et al. Learning Dynamic Dependencies With Graph Evolution Recurrent Unit for Stock Predictions[J]. IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS,2023:13.
APA	Tian, Hu,Zhang, Xingwei,Zheng, Xiaolong,&Zeng, Daniel Dajun.(2023).Learning Dynamic Dependencies With Graph Evolution Recurrent Unit for Stock Predictions.IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS,13.
MLA	Tian, Hu,et al."Learning Dynamic Dependencies With Graph Evolution Recurrent Unit for Stock Predictions".IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2023):13.