A model based LSTM and graph convolutional network for stock trend prediction

Stock market is a complex system characterized by collective activity, where interdependencies between stocks have a significant influence on stock price trends. It is widely believed that modeling these dependencies can improve the accuracy of stock trend prediction and enable investors to earn mor...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiangdong Ran, Zhiguang Shan, Yukang Fan, Lei Gao
Format: Article
Language:English
Published: PeerJ Inc. 2024-09-01
Series:PeerJ Computer Science
Subjects:
Online Access:https://peerj.com/articles/cs-2326.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850262239043387392
author Xiangdong Ran
Zhiguang Shan
Yukang Fan
Lei Gao
author_facet Xiangdong Ran
Zhiguang Shan
Yukang Fan
Lei Gao
author_sort Xiangdong Ran
collection DOAJ
description Stock market is a complex system characterized by collective activity, where interdependencies between stocks have a significant influence on stock price trends. It is widely believed that modeling these dependencies can improve the accuracy of stock trend prediction and enable investors to earn more stable profits. However, these dependencies are not directly observable and need to be analyzed from stock data. In this paper, we propose a model based on Long short-term memory (LSTM) and graph convolutional network to capture these dependencies for stock trend prediction. Specifically, an LSTM is employed to extract the stock features, with all hidden state outputs utilized to construct the graph nodes. Subsequently, Pearson correlation coefficient is used to organize the stock features into a graph structure. Finally, a graph convolutional network is applied to extract the relevant features for accurate stock trend prediction. Experiments based on China A50 stocks demonstrate that our proposed model outperforms baseline methods in terms of prediction performance and trading backtest returns. In trading backtest, we have identified a set of effective trading strategies as part of the trading plan. Based on China A50 stocks, our proposed model shows promising results in generating desirable returns during both upward and downward channels of the stock market. The proposed model has proven beneficial for investors to seeking optimal timing and pricing when dealing with shares.
format Article
id doaj-art-9993d19d06fc4094b1fb66e34cee2e57
institution OA Journals
issn 2376-5992
language English
publishDate 2024-09-01
publisher PeerJ Inc.
record_format Article
series PeerJ Computer Science
spelling doaj-art-9993d19d06fc4094b1fb66e34cee2e572025-08-20T01:55:12ZengPeerJ Inc.PeerJ Computer Science2376-59922024-09-0110e232610.7717/peerj-cs.2326A model based LSTM and graph convolutional network for stock trend predictionXiangdong Ran0Zhiguang Shan1Yukang Fan2Lei Gao3Beijing Information Technology College, Beijing, ChinaInformatization and Industry Research Department, State Information Center, Beijing, ChinaCollege of Arts and Science, New York University, New York, United States of AmericaStandards and Safety Department, Beijing Big Data Center, Beijing, ChinaStock market is a complex system characterized by collective activity, where interdependencies between stocks have a significant influence on stock price trends. It is widely believed that modeling these dependencies can improve the accuracy of stock trend prediction and enable investors to earn more stable profits. However, these dependencies are not directly observable and need to be analyzed from stock data. In this paper, we propose a model based on Long short-term memory (LSTM) and graph convolutional network to capture these dependencies for stock trend prediction. Specifically, an LSTM is employed to extract the stock features, with all hidden state outputs utilized to construct the graph nodes. Subsequently, Pearson correlation coefficient is used to organize the stock features into a graph structure. Finally, a graph convolutional network is applied to extract the relevant features for accurate stock trend prediction. Experiments based on China A50 stocks demonstrate that our proposed model outperforms baseline methods in terms of prediction performance and trading backtest returns. In trading backtest, we have identified a set of effective trading strategies as part of the trading plan. Based on China A50 stocks, our proposed model shows promising results in generating desirable returns during both upward and downward channels of the stock market. The proposed model has proven beneficial for investors to seeking optimal timing and pricing when dealing with shares.https://peerj.com/articles/cs-2326.pdfLong short-term memoryGraph convolutional networkStock trend predictionStock trading decisions
spellingShingle Xiangdong Ran
Zhiguang Shan
Yukang Fan
Lei Gao
A model based LSTM and graph convolutional network for stock trend prediction
PeerJ Computer Science
Long short-term memory
Graph convolutional network
Stock trend prediction
Stock trading decisions
title A model based LSTM and graph convolutional network for stock trend prediction
title_full A model based LSTM and graph convolutional network for stock trend prediction
title_fullStr A model based LSTM and graph convolutional network for stock trend prediction
title_full_unstemmed A model based LSTM and graph convolutional network for stock trend prediction
title_short A model based LSTM and graph convolutional network for stock trend prediction
title_sort model based lstm and graph convolutional network for stock trend prediction
topic Long short-term memory
Graph convolutional network
Stock trend prediction
Stock trading decisions
url https://peerj.com/articles/cs-2326.pdf
work_keys_str_mv AT xiangdongran amodelbasedlstmandgraphconvolutionalnetworkforstocktrendprediction
AT zhiguangshan amodelbasedlstmandgraphconvolutionalnetworkforstocktrendprediction
AT yukangfan amodelbasedlstmandgraphconvolutionalnetworkforstocktrendprediction
AT leigao amodelbasedlstmandgraphconvolutionalnetworkforstocktrendprediction
AT xiangdongran modelbasedlstmandgraphconvolutionalnetworkforstocktrendprediction
AT zhiguangshan modelbasedlstmandgraphconvolutionalnetworkforstocktrendprediction
AT yukangfan modelbasedlstmandgraphconvolutionalnetworkforstocktrendprediction
AT leigao modelbasedlstmandgraphconvolutionalnetworkforstocktrendprediction