Journal article
Inductive Representation Learning on Dynamic Stock Co-Movement Graphs for Stock Predictions
INFORMS journal on computing, Vol.34(4), pp.1940-1957
07/01/2022
DOI: 10.1287/ijoc.2022.1172
Abstract
Co-movement among individual firms' stock prices can reflect complex inter-firm relationships. This paper proposes a novel method to leverage such relationships for stock price predictions by adopting inductive graph representation learning on dynamic stock graphs constructed based on historical stock price co-movement. To learn node representations from such dynamic graphs for better stock predictions, we propose the hybrid-attention dynamic graph neural network, an inductive graph representation learning method. We also extended mini-batch gradient descent to inductive representation learning on dynamic stock graphs so that the model can update parameters over mini-batch stock graphs with higher training efficiency. Extensive experiments on stocks from different markets and trading simulations demonstrate that the proposed method significantly improves stock predictions. The proposed method can have important implications for the management of financial portfolios and investment risk.
Details
- Title: Subtitle
- Inductive Representation Learning on Dynamic Stock Co-Movement Graphs for Stock Predictions
- Creators
- Hu Tian - School of Artificial Intelligence, University of Chinese Academy of Science, Beijing 100190, ChinaXiaolong Zheng - School of Artificial Intelligence, University of Chinese Academy of Science, Beijing 100190, ChinaKang Zhao - University of IowaMaggie Wenjing Liu - Tsinghua UniversityDaniel Dajun Zeng - School of Artificial Intelligence, University of Chinese Academy of Science, Beijing 100190, China
- Resource Type
- Journal article
- Publication Details
- INFORMS journal on computing, Vol.34(4), pp.1940-1957
- Publisher
- Informs
- DOI
- 10.1287/ijoc.2022.1172
- ISSN
- 1091-9856
- eISSN
- 1526-5528
- Number of pages
- 18
- Grant note
- XDA27030100 / Strategic Priority Research Programof Chinese Academy of Sciences; Chinese Academy of Sciences 2017ZX10303401-002 / Ministry of Health of China 71621002; 71472175; 71602184; 71991462; 71825007 / Natural Science Foundation of China; National Natural Science Foundation of China (NSFC) 2020AAA0108401 / Ministry of Science and Technology of China; Ministry of Science and Technology, China
- Language
- English
- Date published
- 07/01/2022
- Academic Unit
- Business Analytics
- Record Identifier
- 9984380508402771
Metrics
4 Record Views