Phuoc Long. Phan; The Khai. Phan; Van Thanh. Nguyen; Thi Huong. Tran

A Dynamic Dual-Graph GCN-GRU Framework for Stock Movement Prediction

PDF (1035KB), PP.190-216

Views: 0 Downloads: 0

Author(s)

Phuoc Long. Phan ¹ The Khai. Phan ^1,* Van Thanh. Nguyen ¹ Thi Huong. Tran ¹

1. Academy of Finance, Hanoi, 100000, Vietnam

* Corresponding author.

DOI: https://doi.org/10.5815/ijitcs.2026.05.12

Received: 5 Apr. 2026 / Revised: 8 Jun. 2026 / Accepted: 17 Aug. 2026 / Published: 8 Oct. 2026

Index Terms

Stock Movement Prediction, Dual-graph Learning, Graph Convolutional Network, Gated Recurrent Unit, Dynamic Correlation Graph, Financial Time Series

Abstract

Stock movement prediction is a challenging task due to the complex temporal dynamics of financial time series and the interdependence among stocks. Most existing approaches either model each stock independently or rely on a single static graph, which limits their ability to capture heterogeneous and time-varying relationships in financial markets. To address this issue, this paper proposes a dynamic dual-graph GCN-GRU framework for next-day stock movement prediction. The proposed model integrates two complementary graph structures: a static industry graph to encode long-term sectoral relationships and a dynamic correlation graph to capture evolving co-movement patterns among stocks over time, where the dynamic graph is constructed in a causally consistent manner using only historical information available before the target prediction. For each graph, a graph convolutional network (GCN) is employed to learn relational stock representations, while a gated recurrent unit (GRU) is used to model temporal dependencies from sequential graph-based embeddings. The two graph-specific representations are integrated through an adaptive gated fusion mechanism. By jointly exploiting structural market information and temporal dynamics, the proposed framework provides a unified representation for next-day stock direction forecasting. Experiments are conducted on two public stock datasets constructed from the S&P 500 and VN30 markets using engineered features derived from daily trading data. The evaluation considers both standard classification metrics and finance-oriented indicators, including IC, Sharpe ratio, and maximum drawdown. The empirical results demonstrate the effectiveness of the proposed approach compared with conventional machine learning, sequence-based, and graph-based baselines. These findings suggest that combining dynamic relational modeling with temporal learning is a practical and reproducible forecasting framework for stock movement prediction in both developed and emerging markets.

Cite This Paper

Phuoc Long. Phan, The Khai. Phan, Van Thanh. Nguyen, Thi Huong. Tran, "A Dynamic Dual-Graph GCN-GRU Framework for Stock Movement Prediction", International Journal of Information Technology and Computer Science(IJITCS), Vol.18, No.5, pp.190-216, 2026. DOI:10.5815/ijitcs.2026.05.12

Reference

[1]E. F. Fama, “Efficient capital markets: A review of theory and empirical work,” Journal of Finance, vol. 25, no. 2, pp. 383–417, 1970.
[2]A. R. Calingo, A. M. Sison, and B. T. Tanguilig III, “Prediction model of the stock market index using Twitter˜ sentiment analysis,” International Journal of Information Technology and Computer Science, vol. 8, no. 10, pp. 11–21, 2016.
[3]P. P. Dey, N. Nahar, and B. M. M. Hossain, “Forecasting stock market trend using machine learning algorithms with technical indicators,” International Journal of Information Technology and Computer Science, vol. 12, no. 3, pp. 32–38, 2020.
[4]F. W. Christanto, V. G. Utomo, R. Prathivi, and C. Dewi, “The impact of financial statement integration in machine learning for stock price prediction,” International Journal of Information Technology and Computer Science, vol. 16, no. 1, pp. 35–42, 2024.
[5]M. Kolambe and S. Arora, “Comparative analysis of LSTM variants for stock price forecasting on NSE India: GRU’s dominance and enhancements,” International Journal of Information Technology and Computer Science, vol. 16, no. 6, pp. 43–60, 2024.
[6]K. Cho, B. van Merrienboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, “Learning phrase¨ representations using RNN encoder–decoder for statistical machine translation,” in Proc. 2014 Conf. on Empirical Methods in Natural Language Processing (EMNLP), 2014, pp. 1724–1734.
[7]T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” in Proc. 5th Int. Conf. on Learning Representations (ICLR), 2017.
[8]F. Feng, H. Chen, X. He, J. Ding, M. Sun, and T.-S. Chua, “Temporal relational ranking for stock prediction,” ACM Transactions on Information Systems, vol. 37, no. 2, Art. no. 27, pp. 1–30, 2019.
[9]W. Li, R. Bao, K. Harimoto, D. Chen, J. Xu, and Q. Su, “Modeling the stock relation with graph network for overnight stock movement prediction,” in Proc. 29th Int. Joint Conf. on Artificial Intelligence (IJCAI), 2020, pp. 4541–4547.
[10]W. Chen, M. Jiang, W.-G. Zhang, and Z. Chen, “A novel graph convolutional feature based convolutional neural network for stock trend prediction,” Information Sciences, vol. 556, pp. 67–94, 2021.
[11]Q. Chen and C.-Y. Robert, “Graph-based learning for stock movement prediction with textual and relational data,” The Journal of Financial Data Science, vol. 4, no. 4, pp. 152–166, 2022.
[12]S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.
[13]Y. Qin, D. Song, H. Chen, W. Cheng, G. Jiang, and G. Cottrell, “A dual-stage attention-based recurrent neural network for time series prediction,” in Proc. 26th Int. Joint Conf. on Artificial Intelligence (IJCAI), 2017, pp. 2627– 2633.
[14]Y. Xu and S. B. Cohen, “Stock movement prediction from tweets and historical prices,” in Proc. 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2018, pp. 1970–1979.
[15]F. Feng, X. He, X. Wang, C. Luo, Y. Liu, and T.-S. Chua, “Enhancing stock movement prediction with adversarial training,” in Proc. 28th Int. Joint Conf. on Artificial Intelligence (IJCAI), 2019, pp. 5843–5849.
[16]X. Li, J. Wang, J. Tan, S. Ji, and H. Jia, “A graph neural network-based stock forecasting method utilizing multisource heterogeneous data fusion,” Multimedia Tools and Applications, vol. 81, no. 30, pp. 43753–43775, 2022.
[17]H. Peng, K. Dong, and J. Yang, “Stock price movement prediction based on relation type guided graph convolutional network,” Engineering Applications of Artificial Intelligence, vol. 126, Art. no. 106948, 2023.
[18]R. Kim, C. H. So, M. Jeong, S. Lee, J. Kim, and J. Kang, “HATS: A hierarchical graph attention network for stock movement prediction,” arXiv preprint arXiv:1908.07999, 2019.
[19]D. Cheng, F. Yang, S. Xiang, and J. Liu, “Financial time series forecasting with multi-modality graph neural network,” Pattern Recognition, vol. 121, Art. no. 108218, 2022.
[20]H. Qian, H. Zhou, Q. Zhao, H. Chen, H. Yao, J. Wang, Z. Liu, F. Yu, Z. Zhang, and J. Zhou, “MDGNN: Multirelational dynamic graph neural network for comprehensive and dynamic stock investment prediction,” in Proc. AAAI Conf. on Artificial Intelligence, vol. 38, no. 13, 2024, pp. 14642–14650.
[21]D. Ma, D. Yuan, M. Huang, and L. Dong, “VGC-GAN: A multi-graph convolution adversarial network for stock price prediction,” Expert Systems with Applications, vol. 236, Art. no. 121204, 2024.
[22]J. Ye, J. Zhao, K. Ye, and C. Xu, “Multi-graph convolutional network for relationship-driven stock movement prediction,” in Proc. 25th Int. Conf. on Pattern Recognition (ICPR), 2021, pp. 6702–6709.
[23]S&P Dow Jones Indices, “S&P 500®,” [Online]. Available: https://www.spglobal.com/spdji/en/ indices/equity/sp-500/. Accessed: Mar. 23, 2026.
[24]R. Aroussi, “yfinance.download,” [Online]. https://ranaroussi.github.io/yfinance/reference/api/yfinance.download.html, Accessed: Mar. 23, 2026.
[25]Ho Chi Minh City Stock Exchange, “HOSE-Index Series,” Feb. 2025. [Online]. Available: https: //static2.vietstock.vn/vietstock/2025/2/12/20250212_form_factsheet_mcindices_ eng_t02_2025.pdf. Accessed: Mar. 23, 2026.
[26]Vnstock, “Thng keˆ gia´ lch s,” [Online]. Available: https://vnstocks.com/docs/vnstock/ thong-ke-gia-lich-su. Accessed: Mar. 23, 2026.
[27]A. Pareja, G. Domeniconi, J. Chen, T. Ma, T. Suzumura, H. Kanezashi, T. Kaler, T. B. Schardl, and C. E. Leiserson, “EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 04, pp. 5363–5370, 2020.
[28]J. H. Friedman, “Greedy Function Approximation: A Gradient Boosting Machine,” The Annals of Statistics, vol. 29, no. 5, pp. 1189–1232, 2001.
[29]F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.
[30]G. Ke, Q. Meng, T. Finley, T. Wang, W. Chen, W. Ma, Q. Ye, and T.-Y. Liu, “LightGBM: A Highly Efficient Gradient Boosting Decision Tree,” in Advances in Neural Information Processing Systems, vol. 30, pp. 3146–3154, 2017.

International Journal of Information Technology and Computer Science (IJITCS)