Abstract
Stock prices movement prediction has been a longstanding research topic. Many studies have introduced several kinds of external information like relations of stocks, combined with internal information of trading characteristics to promote forecasting. Different from previous cases, this article proposes a reasonable assumption that major fluctuations of stock prices are mainly triggered by high-volume transactions which usually occur on a group of stocks that share some common features (e.g., stocks in the same industry, region, concept or yield similar volatility), and further develops an integrated GCN-LSTM method to achieve more precise predictions from the perspective of modelling capital flows. First, we construct four kinds of graphs incorporating various relational knowledge (edge) and utilize graph convolutional network (GCN) to extract stock (node) embeddings in multiple time-periods. Then, the obtained temporal sequences of stock embeddings are put into long short-term memory recurrent neural network (LSTM) to discriminate the moving direction of prices. Extensive experiments on major Chinese stock indexes have demonstrated the effectiveness of our model with best accuracy of 57.81% acquired, which is much better than baselines. Moreover, experimental results of GCN-LSTM under different graphs and various node embedding dimensions have been compared and analyzed, indicating the selection of key parameters to achieve optimal performances. Our research findings provide an improved model to forecast stock prices movement directions with a reliable theoretical interpretation, and in depth exhibit insights for further applications of graph neural networks and graph data in business analytics, quantitative finance, and risk management decision-makings.
Similar content being viewed by others
Data availability statement
All stock prices and indicators utilized in experiments are collected from a major financial information provider in China, Wind Information Co., Ltd (https://www.wind.com.cn/Default.html).
References
Attig N, Fong WM, Gadhoum Y, Lang LHP (2006) Effects of large shareholding on information asymmetry and stock liquidity. J Bank Finance 30(10):2875–2892. https://doi.org/10.1016/j.jbankfin.2005.12.002
Babu CN, Reddy BE (2014) A moving-average filter based hybrid arima-ann model for forecasting time series data. Appl Soft Comput 23:27–38. https://doi.org/10.1016/j.asoc.2014.05.028
Bhosale YH, Patnaik KS (2022) Application of deep learning techniques in diagnosis of COVID-19 (coronavirus): a systematic review. Neural Process Lett. https://doi.org/10.1007/s11063-022-11023-0
Bildirici M, Ersin Özgür Ömer (2009) Improving forecasts of garch family models with the artificial neural networks: an application to the daily returns in Istanbul stock exchange. Expert Syst Appl 36(4):7355–7362. https://doi.org/10.1016/j.eswa.2008.09.051
Chandola D, Mehta A, Singh S, Tikkiwal VA, Agrawal H (2022) Forecasting directional movement of stock prices using deep learning. Ann Data Sci. https://doi.org/10.1007/s40745-022-00432-6
Chandar S K (2021) Hybrid models for intraday stock price forecasting based on artificial neural networks and metaheuristic algorithms. Pattern Recognit Lett 147:124–133. https://doi.org/10.1016/j.patrec.2021.03.030
Chen C, Zhao L, Bian J, Liu TY (2019) Investment behaviors can tell what inside: exploring stock intrinsic properties for stock trend prediction. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery and data mining (KDD 2019), Association for Computing Machinery, New York, NY, USA, pp 2376–2384. https://doi.org/10.1145/3292500.3330663
Chen W, Yeo CK, Lau CT, Lee BS (2018) Leveraging social media news to predict stock index movement using RNN-boost. Data Knowl Eng 118:14–24. https://doi.org/10.1016/j.datak.2018.08.003
Chen Y, Wei Z, Huang X (2018) Incorporating corporation relationship via graph convolutional neural networks for stock price prediction. In: Proceedings of the 27th ACM international conference on information and knowledge management (CIKM 2018), Association for Computing Machinery, New York, NY, USA, pp 1655–1658. https://doi.org/10.1145/3269206.3269269
Chen Y, Wu J, Wu Z (2022) China’s commercial bank stock price prediction using a novel k-means-lstm hybrid approach. Expert Syst Appl 202:117370. https://doi.org/10.1016/j.eswa.2022.117370
Chen YC, Huang WC (2021) Constructing a stock-price forecast CNN model with gold and crude oil indicators. Appl Soft Comput 112:107760. https://doi.org/10.1016/j.asoc.2021.107760
Cheng R, Li Q (2021) Modeling the momentum spillover effect for stock prediction via attribute-driven graph attention networks. In: Proceedings of the AAAI conference on artificial intelligence (AAAI 2021), Palo Alto, CA, USA, pp 55–62. https://doi.org/10.1609/aaai.v35i1.16077
Coşkun M, Koyutürk M (2021) Node similarity-based graph convolution for link prediction in biological networks. Bioinformatics 37(23):4501–4508. https://doi.org/10.1093/bioinformatics/btab464
De Pontes LS, Rêgo LC (2022) Impact of macroeconomic variables on the topological structure of the Brazilian stock market: a complex network approach. Phys A Stat Mech Appl 604:127660. https://doi.org/10.1016/j.physa.2022.127660
Derrac J, García S, Molina D, Herrera F (2011) A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms. Swarm Evol Comput 1(1):3–18. https://doi.org/10.1016/j.swevo.2011.02.002
Emenogu NG, Adenomon MO, Nweze NO (2020) On the volatility of daily stock returns of total Nigeria plc: evidence from garch models, value-at-risk and backtesting. Financ Innov 6(1):1–25. https://doi.org/10.1186/s40854-020-00178-1
Esmaeilpour Moghadam HE, Mohammadi T, Kashani MF, Shakeri A (2019) Complex networks analysis in Iran stock market: the application of centrality. Phys A Stat Mech Appl 531:121800. https://doi.org/10.1016/j.physa.2019.121800
Feng F, He X, Wang X, Luo C, Liu Y, Chua TS (2019) Temporal relational ranking for stock prediction. ACM Trans Inf Syst 37(2):1–30. https://doi.org/10.1145/3309547
Feng S, Xu C, Zuo Y et al (2022) Relation-aware dynamic attributed graph attention network for stocks recommendation. Pattern Recognit 121:108119. https://doi.org/10.1016/j.patcog.2021.108119
Gao J, Ying X, Xu C et al (2021) Graph-based stock recommendation by time-aware relational attention network. ACM Trans Knowl Discov Data 16(1):1–21. https://doi.org/10.1145/3451397
Ghosh P, Neufeld A, Sahoo JK (2022) Forecasting directional movements of stock prices for intraday trading using lstm and random forests. Finance Res Lett 46:102280. https://doi.org/10.1016/j.frl.2021.102280
Gunduz H, Yaslan Y, Cataltepe Z (2017) Intraday prediction of Borsa Istanbul using convolutional neural networks and feature correlations. Knowl Based Syst 137:138–148. https://doi.org/10.1016/j.knosys.2017.09.023
Guoying Z, Ping C (2017) Forecast of yearly stock returns based on adaboost integration algorithm. In: 2017 IEEE international conference on smart cloud, New York, NY, USA, pp 263–267. https://doi.org/10.1109/SmartCloud.2017.49
Hao PY, Kung CF, Chang CY et al (2021) Predicting stock price trends based on financial news articles and using a novel twin support vector machine with fuzzy hyperplane. Appl Soft Comput 98:106806. https://doi.org/10.1016/j.asoc.2020.106806
Hoseinzade E, Haratizadeh S (2019) CNNpred: CNN-based stock market prediction using a diverse set of variables. Expert Syst Appl 129:273–285. https://doi.org/10.1016/j.eswa.2019.03.029
Hou X, Wang K, Zhong C, Wei Z (2021) ST-Trader: a spatial-temporal deep neural network for modeling stock market movement. IEEE/CAA J Autom Sin 8(5):1015–1024. https://doi.org/10.1109/JAS.2021.1003976
Kanwal A, Lau MF, Ng SP et al (2022) BiCuDNNLSTM-1dCNN-a hybrid deep learning-based predictive model for stock price prediction. Expert Syst Appl 202: 117123. https://doi.org/10.1016/j.eswa.2022.117123
Karnyoto AS, Sun C, Liu B et al (2022) Augmentation and heterogeneous graph neural network for AAAI2021-COVID-19 fake news detection. Int J Mach Learn Cybern 13:2033–2043. https://doi.org/10.1007/s13042-021-01503-5
Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: 5th international conference on learning representations (ICLR 2017), Toulon, France. https://openreview.net/pdf?id=SJU4ayYgl
Kohli PPS, Zargar S, Arora S et al (2019) Stock prediction using machine learning algorithms. In: Applications of Artificial Intelligence Techniques in Engineering, Advances in Intelligent Systems and Computing, vol 698, Springer, Singapore, pp 405–414. https://doi.org/10.1007/978-981-13-1819-1_38
Kong A, Zhu H, Azencott R (2021) Predicting intraday jumps in stock prices using liquidity measures and technical indicators. J Forecast 40(3):416–438. https://doi.org/10.1002/for.2721
Kumar R, Kumar P, Kumar Y (2022) Three stage fusion for effective time series forecasting using Bi-LSTM-ARIMA and improved DE-ABC algorithm. Neural Comput Appl 34:18421–18437. https://doi.org/10.1007/s00521-022-07431-x
Li MW, Xu DY, Geng J, Hong WC (2022) A hybrid approach for forecasting ship motion using CNN-GRU-AM and GCWOA. Appl Soft Comput 114:108084. https://doi.org/10.1016/j.asoc.2021.108084
Li W, Bao R, Harimoto K, Chen D, Xu J, Su Q (2020) Modeling the stock relation with graph network for overnight stock movement prediction. In: Proceedings of the 29th international joint conference on artificial intelligence (IJCAI 2020), pp 4541–4547. https://doi.org/10.24963/ijcai.2020/626
Liu G, Ma W (2022) A quantum artificial neural network for stock closing price prediction. Inf Sci 598:75–85. https://doi.org/10.1016/j.ins.2022.03.064
Liu Q, Tao Z, Tse Y et al (2022) Stock market prediction with deep learning: the case of china. Finance Res Lett 46:102209. https://doi.org/10.1016/j.frl.2021.102209
Liu S, Li T, Ding H et al (2020) A hybrid method of recurrent neural network and graph neural network for next-period prescription prediction. Int J Mach Learn Cybern 11(12):2849–2856. https://doi.org/10.1007/s13042-020-01155-x
Lohrmann C, Luukka P (2019) Classification of intraday S&P500 returns with a random forest. Int J Forecast 35(1):390–407. https://doi.org/10.1016/j.ijforecast.2018.08.004
Manessi F, Rozza A (2021) Graph-based neural network models with multiple self-supervised auxiliary tasks. Pattern Recognit Lett 148:15–21. https://doi.org/10.1016/j.patrec.2021.04.021
Nakagawa K, Yoshida K (2022) Time-series gradient boosting tree for stock price prediction. Int J Data Min Model Manag 14(2):110–125. https://doi.org/10.1504/IJDMMM.2022.123357
Pan Y, Xiao Z, Wang X et al (2017) A multiple support vector machine approach to stock index forecasting with mixed frequency sampling. Knowl Based Syst 122:90–102. https://doi.org/10.1016/j.knosys.2017.01.033
Peng H, Du B, Liu M et al (2021) Dynamic graph convolutional network for long-term traffic flow prediction with reinforcement learning. Inf Sci 578:401–416. https://doi.org/10.1016/j.ins.2021.07.007
Peng H, Li J, Wang Z et al (2023) Lifelong property price prediction: a case study for the Toronto real estate market. IEEE Trans Knowl Data Eng 35(3):2765–2780. https://doi.org/10.1109/TKDE.2021.3112749
Qiao J, Wang L, Duan L (2021) Sequence and graph structure co-awareness via gating mechanism and self-attention for session-based recommendation. Int J Mach Learn Cybern 12(9):2591–2605. https://doi.org/10.1007/s13042-021-01343-3
Roll R (1988) R2. J Finance 43(3):541–566. https://doi.org/10.1111/j.1540-6261.1988.tb04591.x
Schlichtkrull M, Kipf TN, Bloem P, van den Berg R, Titov I, Welling M (2018) Modeling relational data with graph convolutional networks. In: The semantic web: European semantic web conference (ESWC 2018), Lecture Notes in Computer Science, vol 10843, Springer, Cham, pp 593–607. https://doi.org/10.1007/978-3-319-93417-4_38
Sezer OB, Ozbayoglu AM (2018) Algorithmic financial trading with deep convolutional neural networks: time series to image conversion approach. Appl Soft Comput 70:525–538. https://doi.org/10.1016/j.asoc.2018.04.024
Tang H, Dong P, Shi Y (2019) A new approach of integrating piecewise linear representation and weighted support vector machine for forecasting stock turning points. Appl Soft Comput 78:685–696. https://doi.org/10.1016/j.asoc.2019.02.039
Wan X, Cen L, Chen X et al (2022) A novel multiple temporal-spatial convolution network for anode current signals classification. Int J Mach Learn Cybern 13:3299–3310. https://doi.org/10.1007/s13042-022-01595-7
Wang L, Ma F, Liu J et al (2020) Forecasting stock price volatility: new evidence from the GARCH-MIDAS model. Int J Forecast 36(2):684–694. https://doi.org/10.1016/j.ijforecast.2019.08.005
Wang X, Li J, Yang L et al (2021) Weakly-supervised learning for community detection based on graph convolution in attributed networks. Int J Mach Learn Cybern 12(12):3529–3539. https://doi.org/10.1007/s13042-021-01400-x
Xie Y, Yao C, Gong M et al (2020) Graph convolutional networks with multi-level coarsening for graph classification. Knowl Based Syst 194:105578. https://doi.org/10.1016/j.knosys.2020.105578
Xu W, Liu W, Xu C, Bian J, Yin J, Liu TY (2021) Rest: relational event-driven stock trend forecasting. In: Proceedings of the Web Conference 2021 (WWW 21), Association for Computing Machinery, New York, NY, USA, pp 1–10. https://doi.org/10.1145/3442381.3450032
Ye J, Zhao J, Ye K, Xu C (2021) Multi-graph convolutional network for relationship-driven stock movement prediction. In: 25th international conference on pattern recognition (ICPR), Milan, Italy, pp 6702–6709. https://doi.org/10.1109/ICPR48806.2021.941269
Yin X, Yan D, Almudaifer A, Yan S, Zhou Y (2021) Forecasting stock prices using stock correlation graph: a graph convolutional network approach. In: 2021 international joint conference on neural networks (IJCNN), Shenzhen, China, pp 1–8. https://doi.org/10.1109/IJCNN52387.2021.9533510
Yujun Y, Yimei Y, Wang Z (2021) Research on a hybrid prediction model for stock price based on long short-term memory and variational mode decomposition. Soft Comput 25(21):13513–13531. https://doi.org/10.1007/s00500-021-06122-4
Zhang Z, Hong WC (2021) Application of variational mode decomposition and chaotic grey wolf optimizer with support vector regression for forecasting electric loads. Knowl Based Syst 228:107297. https://doi.org/10.1016/j.knosys.2021.107297
Zhao J, Zeng D, Liang S, Kang H, Liu Q (2021) Prediction model for stock price trend based on recurrent neural network. J Ambient Intell Humaniz Comput 12(1):745–753. https://doi.org/10.1007/s12652-020-02057-0
Zhong X, Enke D (2017) Forecasting daily stock market return using dimensionality reduction. Expert Syst Appl 67:126–139. https://doi.org/10.1016/j.eswa.2016.09.027
Zhou F, Zhang Q, Sornette D, Jiang L (2019) Cascading logistic regression onto gradient boosted decision trees for forecasting and trading stock indices. Appl Soft Comput 84:105747. https://doi.org/10.1016/j.asoc.2019.105747
Acknowledgements
All authors express sincere gratitude to reviewers and editors of International Journal of Machine Learning and Cybernetics for their valuable comments and careful work, with special thanks to Dr. Yunlong Mi from Central South University for his insights and supports that helped this work improved substantially.
Funding
This work has been supported by Key Projects (Grants number 71932008, 72231010) and Youth Project (Grant number 71901155) of National Natural Science Foundation of China.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
All authors have no relevant conflict of interests to declare.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Shi, Y., Wang, Y., Qu, Y. et al. Integrated GCN-LSTM stock prices movement prediction based on knowledge-incorporated graphs construction. Int. J. Mach. Learn. & Cyber. 15, 161–176 (2024). https://doi.org/10.1007/s13042-023-01817-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-023-01817-6