Predicting Stock Market Movements Through Multi-source Data Fusion Graphs: An Approach Employing Graph Convolutional Neural Network
Predicting Stock Market Movements Through Multi-source Data Fusion Graphs: An Approach Employing Graph Convolutional Neural Network |
||
 |
 |
|
| © 2024 by IJETT Journal | ||
| Volume-72 Issue-6 |
||
| Year of Publication : 2024 | ||
| Author : John Ranjith, S. Kumar Chandar |
||
| DOI : 10.14445/22315381/IJETT-V72I6P102 | ||
How to Cite?
John Ranjith, S. Kumar Chandar, "Predicting Stock Market Movements Through Multi-source Data Fusion Graphs: An Approach Employing Graph Convolutional Neural Network," International Journal of Engineering Trends and Technology, vol. 72, no. 6, pp. 8-18, 2024. Crossref, https://doi.org/10.14445/22315381/IJETT-V72I6P102
Abstract
The stock market plays an important role in the capital market, and investigating price fluctuations in the stock market has consistently been a prominent subject for researchers. The application of soft computing techniques to predict and categorize stock market movements is a significant research challenge that has gathered considerable attention from researchers. Although several studies highlight the significance of incorporating information from two sources in stock movement prediction, the potential of advanced graphical techniques for modeling and analyzing multi-source data remains an unattended research area. This study aims to address this gap by introducing a novel model that utilizes multi-source data fusion graphs to predict future market movements. The primary challenge involves establishing a model that can effectively gather the relationships among various data sources and employ this understanding to improve prediction performance. Compared to several existing methods relying only on historical data or sentiment data, which show limited predictive power and lack generality, the proposed approach seeks to overcome these limitations. The proposed model integrates various information sources, including historical prices, news data, Twitter data, and technical indicators for predicting future stock market trends. This presented method involves constructing a subgraph map for each data type to capture events from both rising and falling markets. Then, a Gated recurrent unit (GRU) is employed to aggregate the subgraph nodes. These aggregated nodes are then integrated with a Graph convolutional neural network (GCNN) to classify the multi-source graph, therefore achieving stock market trend prediction effectively. To further validate its effectiveness, the presented model is applied to Indian stock market data, demonstrating its feasibility in fusing multi-source stock data and establishing its suitability for effectively predicting stock market movements.
Keywords
Data fusion, Multi-source data, Graph convolution neural network, Gated recurrent unit, Multi-source data fusion graphs, Stock market trends, Stock trend prediction.
References
[1] Akhter Mohiuddin Rather, V.N. Sastry, and Arun Agarwal, “Stock Market Prediction and Portfolio Selection Models: A Survey,” OPSEARCH, vol. 54, pp. 558-579, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[2] O. Bustos, and A. Pomares-Quimbaya, “Stock Market Movement Forecast: A Systematic Review,” Expert Systems with Applications, vol. 156, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Robert D. Edwards, John Magee, and W.H.C. Bassetti, Technical Analysis of Stock Trends, 11th ed., CRC Press, pp. 1-686, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Yakup Kara, Melek Acar Boyacioglu, and Ömer Kaan Baykan, “Predicting Direction of Stock Price Index Movement Using Artificial Neural Networks and Support Vector Machines: The Sample of the Istanbul Stock Exchange,” Expert Systems with Applications, vol. 38, no. 5, pp. 5311-5319, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Mingyue Qiu, Yu Song, and Fumio Akagi, "Application of Artificial Neural Network for the Prediction of Stock Market Returns: The Case of the Japanese Stock Market,” Chaos, Solitons & Fractals, vol. 85, pp. 1-7, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Xiao Zhong, and David Enke, “Forecasting Daily Stock Market Return Using Dimensionality Reduction,” Expert Systems with Applications, vol. 67, pp. 126-139, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Qianyi Xiao, and Baha Ihnaini, “Stock Trend Prediction Using Sentiment Analysis,” PeerJ Computer Science, vol. 9, pp. 1-18, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Kalyani Joshi, H.N. Bharathi, and Jyothi Rao, “Stock Trend Prediction Using News Sentiment Analysis,” International Journal of Computer Science and Information Technology, vol. 8, no. 3, pp. 67-76, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Manuel R. Vargas, Beatriz S.L.P. de Lima, and Alexandre G. Evsukoff, “Deep Learning for Stock Market Prediction from Financial News Articles,” 2017 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications, Annecy, France, pp. 60-65, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Shilpa Gite et al., “Explainable Stock Prices Prediction from Financial News Articles Using Sentiment Analysis,” PeerJ Computer Science, vol. 7, pp. 1-21, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Sushree Das et al., “Real-Time Sentiment Analysis of Twitter Streaming Data for Stock Prediction,” Procedia Computer Science, vol. 132, pp. 956-964, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Arash Negahdari Kia, Saman Haratizadeh, and Saeed Bagheri Shouraki, “A Hybrid Supervised Semi-Supervised Graph-Based Model to Predict One-Day Ahead Movement of Global Stock Markets and Commodity Prices,” Expert Systems with Applications, vol. 105, pp. 159-173, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Yahoofinance, Finance Yahoo. [Online]. Available: www.yahoofinance.com
[14] Natural Language Toolkit, NLTK, 2023. [Online]. Available: https://www.nltk.org
[15] Edward Loper, and Steven Bird, “NLTK: The Natural Language Toolkit,” Proceedings of the ACL-02 Workshop on Effective Tools and Methodologies for Teaching Natural Language Processing and Computational Linguistics, Philadelphia Pennsylvania, vol. 1, pp. 63-70, 2002.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Jun Wang et al., “A Graph-Based Approach to Multi-Source Heterogeneous Information Fusion in Stock Market,” Plos One, vol. 17, no. 8, pp. 1-23, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Thomas N. Kipf, and Max Welling, “Semi-Supervised Classification with Graph Convolutional Networks,” arXiv, pp. 1-14, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Michaël Defferrard, Xavier Bresson, and Pierre Vandergheynst, “Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering,” arXiv, pp. 1-9, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Qiang QU, Hongtao YU, and Ruiyang Huang, “Spammer Detection Technology of Social Network Based on Graph Convolution Network,” Chinese Journal of Network and Information Security, vol. 4, no. 5, pp. 39-46, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Yingjun Chen, and Yongtao Hao, “A Feature Weighted Support Vector Machine and K-Nearest Neighbor Algorithm for Stock Market Indices Prediction,” Expert Systems with Applications, vol. 80, pp. 340-355, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Xi Zhang et al., “Improving Stock Market Prediction via Heterogeneous Information Fusion,” Knowledge-Based Systems, vol. 143, pp. 236-247, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Lei Chai et al., “A Multi-Source Heterogeneous Data Analytic Method for Future Price Fluctuation Prediction,” Neurocomputing, vol. 418, pp. 11-20, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Qun Zhang, Lijun Yang, and Feng Zhou, “Attention Enhanced Long Short-Term Memory Network with Multi-Source Heterogeneous Information Fusion: An Application to BGI Genomics,” Information Sciences, vol. 553, pp. 305-330, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Qing Li et al., "Tensor-Based Learning for Predicting Stock Movements,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 29, no. 1, pp. 1784-1790, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Xiaohan Li et al., “A Graph Neural Network-Based Stock Forecasting Method Utilizing Multi-Source Heterogeneous Data Fusion,” Multimedia Tools and Applications, vol. 81, no. 30, pp. 43753-43775, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Taylan Kabbani, and Fatih Enes Usta, “Predicting The Stock Trend Using News Sentiment Analysis and Technical Indicators in Spark,” arXiv, pp. 1-4, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Yu Ma et al., “Multi-Source Aggregated Classification for Stock Price Movement Prediction,” Information Fusion, vol. 91, pp. 515528, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Andreas Theissler et al., “Explainable AI for Time Series Classification: A Review, Taxonomy and Research Directions,” IEEE Access, vol. 10, pp. 100700-100724, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Junaid Maqbool et al., “Stock Prediction by Integrating Sentiment Scores of Financial News and MLP-Regressor: A Machine Learning Approach,” Procedia Computer Science, vol. 218, pp. 1067-1078, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Paraskevas Koukaras, Christina Nousi, and Christos Tjortjis, “Stock Market Prediction Using Microblogging Sentiment Analysis and Machine Learning,” Telecom, vol. 3, no. 2, pp. 358-378, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Xi Chen et al., “A Model Fusion Method Based on Multi-Source Heterogeneous Data for Stock Trading Signal Prediction,” Soft Computing, vol. 27, no. 10, pp. 6587-6611, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Aihua Li et al., “Research on Stock Price Prediction from a Data Fusion Perspective,” Data Science in Finance and Economics, vol. 3, no. 3, pp. 230-250, 2023.
[CrossRef] [Google Scholar] [Publisher Link]