Vol 20 No 2 (2026): BAREKENG: Journal of Mathematics and Its Application
Articles

HETEROGENEOUS GRAPH NEURAL NETWORKS FOR STOCK PRICE PREDICTION: MODELING TEMPORAL AND CROSS-STOCK DEPENDENCIES

PDF
  • Hilmi Aziz Bukhori,
  • Elayaraja Aruchunan,
  • Syaiful Anam,
  • Saiful Bukhori,
  • Avin Maulana
Hilmi Aziz Bukhori
Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Brawijaya, Indonesia
Elayaraja Aruchunan
Department of Decision Science, Faculty of Business and Economics, University of Malaya, Malaysia
Syaiful Anam
Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Brawijaya, Indonesia
Saiful Bukhori
Department of Information Technology, Faculty of Computer Science, Universitas Jember, Indonesia
Avin Maulana
Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Brawijaya, Indonesia
DOI: https://doi.org/10.30598/barekengvol20iss2pp0981-1000
Published January 26, 2026
Keywords
  • Stock price prediction,
  • Graph neural networks (GNN),
  • Long short-term memory (LSTM)
How to Cite
[1]
H. A. Bukhori, E. Aruchunan, S. Anam, S. Bukhori, and A. Maulana, “HETEROGENEOUS GRAPH NEURAL NETWORKS FOR STOCK PRICE PREDICTION: MODELING TEMPORAL AND CROSS-STOCK DEPENDENCIES”, BAREKENG: J. Math. & App., vol. 20, no. 2, pp. 0981-1000, Jan. 2026.

Copyright (c) 2026 Hilmi Aziz Bukhori, Elayaraja Aruchunan, Syaiful Anam, Saiful Bukhori, Avin Maulana

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Abstract

Stock price prediction remains a challenging task due to the complex interplay of temporal trends and relational dependencies within financial markets. This study proposes the GNN-LSTM Hybrid model, a novel framework that integrates Graph Neural Networks (GNNs) with Long Short-Term Memory (LSTM) units to simultaneously capture heterogeneous graph structures and temporal dynamics in stock data, leveraging GNNs to model relational dependencies and LSTMs to address long-term temporal patterns, with graph construction based on stock correlation and temporal edge features. Using a dataset covering 1,270 trading days from March 2015 to April 2020, we evaluate the model against traditional methods (ARIMA, LSTM) and modern graph-based approaches (T-GCN, GAT, Transformer-TS, Base GraphSAGE, SAGE-IS). The GNN-LSTM Hybrid achieves superior performance, with a Mean Absolute Error (MAE) of 0.740 (±0.13), Root Mean Squared Error (RMSE) of 1.100 (±0.21), Mean Absolute Percentage Error (MAPE) of 4.92% (±1.16), and Directional Accuracy (DA) of 67.0% (±2.7), and significantly outperforms all baselines, as confirmed by paired t-tests (p < 0.05). Hyperparameter analysis reveals that a configuration of 6 GNN layers and a hidden dimension size of 128 optimizes predictive accuracy, balancing computational efficiency (training time: 16.0 ± 0.7 s) and performance. Validation across 100 training epochs further confirms the model’s robust convergence across all metrics. With an inference time of 20.0 ± 1.0 ms, which is competitive compared to baselines like ARIMA (23.5 ± 1.1 ms) and GAT (20.5 ± 1.0 ms), the GNN-LSTM Hybrid demonstrates strong potential for practical financial forecasting, offering a scalable and accurate solution for capturing the multifaceted dynamics of stock markets, with implications for real-time applications and broader economic modeling.

PDF

Downloads

Download data is not yet available.

References

  1. V. Ravi et al., “GENERATIVE AI FOR FINANCIAL FORECASTING AND PORTFOLIO OPTIMIZATION.”
  2. K. Olorunnimbe and H. Viktor, “DEEP LEARNING IN THE STOCK MARKET—A SYSTEMATIC SURVEY OF PRACTICE, BACKTESTING, AND APPLICATIONS,” Artif Intell Rev, vol. 56, no. 3, pp. 2057–2109, Mar. 2023, doi: https://doi.org/10.1007/s10462-022-10226-0.
  3. S. Karamolegkos and D. E. Koulouriotis, “ADVANCING SHORT-TERM LOAD FORECASTING WITH DECOMPOSED FOURIER ARIMA: A CASE STUDY ON THE GREEK ENERGY MARKET,” Energy, vol. 325, Jun. 2025, doi: https://doi.org/10.1016/j.energy.2025.135854.
  4. B. R. Lamichhane, M. Isnan, and T. Horanont, “EXPLORING MACHINE LEARNING TRENDS IN POVERTY MAPPING: A REVIEW AND META-ANALYSIS,” Jun. 01, 2025, Elsevier B.V. doi: https://doi.org/10.1016/j.srs.2025.100200.
  5. M. Mohtasam Hossain Sizan et al., “JOURNAL OF BUSINESS AND MANAGEMENT STUDIES AI-ENHANCED STOCK MARKET PREDICTION: EVALUATING MACHINE LEARNING MODELS FOR FINANCIAL FORECASTING IN THE USA,” 2023, doi: https://doi.org/10.32996/jbms
  6. X. Li et al, “ScaleGNN: TOWARDS SCALABLE GRAPH NEURAL NETWORKS VIA ADAPTIVE HIGH-ORDER NEIGHBORING FEATURE FUSION,” Apr. 2025, [Online]. Available: http://arxiv.org/abs/2504.15920
  7. S. Wettewa, L. Hou, and G. Zhang, “GRAPH NEURAL NETWORKS FOR BUILDING AND CIVIL INFRASTRUCTURE OPERATION AND MAINTENANCE ENHANCEMENT,” Oct. 01, 2024, Elsevier Ltd. doi: https://doi.org/10.1016/j.aei.2024.102868.
  8. W. Bao et al,“DATA-DRIVEN STOCK FORECASTING MODELS BASED ON NEURAL NETWORKS: A REVIEW,” Information Fusion, vol. 113, Jan. 2025, doi: https://doi.org/10.1016/j.inffus.2024.102616.
  9. F. Corradini, M. Gori, C. Lucheroni, M. Piangerelli, and M. Zannotti, “A SYSTEMATIC LITERATURE REVIEW OF SPATIO-TEMPORAL GRAPH NEURAL NETWORK MODELS FOR TIME SERIES FORECASTING AND CLASSIFICATION,” Oct. 2024, [Online]. doi: https://doi.org/10.1016/j.neunet.2025.108269
  10. X. Hu et al., “SELF-EXPLAINABLE GRAPH NEURAL NETWORK FOR ALZHEIMER DISEASE AND RELATED DEMENTIAS RISK PREDICTION: ALGORITHM DEVELOPMENT AND VALIDATION STUDY,” JMIR Aging, vol. 7, 2024, doi: https://doi.org/10.2196/54748.
  11. H. A. Bukhori and R. Munir, “INDUCTIVE LINK PREDICTION BANKING FRAUD DETECTION SYSTEM USING HOMOGENEOUS GRAPH-BASED MACHINE LEARNING MODEL,” in 2023 IEEE 13th Annual Computing and Communication Workshop and Conference, CCWC 2023, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 246–251. doi: https://doi.org/10.1109/CCWC57344.2023.10099180.
  12. X. Gao et al., “UNCERTAINTY-AWARE PROBABILISTIC GRAPH NEURAL NETWORKS FOR ROAD-LEVEL TRAFFIC CRASH PREDICTION,” Accid Anal Prev, vol. 208, Dec. 2024, doi: https://doi.org/10.1016/j.aap.2024.107801.
  13. F. F. Mojtahedi, N. Yousefpour, S. H. Chow, and M. Cassidy, “DEEP LEARNING FOR TIME SERIES FORECASTING: REVIEW AND APPLICATIONS IN GEOTECHNICS AND GEOSCIENCES,” 2025, Springer Science and Business Media B.V. doi: https://doi.org/10.1007/s11831-025-10244-5.
  14. P. S. Rana et al, “COMPARATIVE ANALYSIS OF TREE-BASED MODELS AND DEEP LEARNING ARCHITECTURES FOR TABULAR DATA: PERFORMANCE DISPARITIES AND UNDERLYING FACTORS,” in Proceedings - 2023 International Conference on Advanced Computing and Communication Technologies, ICACCTech 2023, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 224–231. doi: https://doi.org/10.1109/ICACCTech61146.2023.00044.
  15. A. A. Mir, M. F. Zuhairi, S. Musa, M. H. Alanazi, and A. Namoun, “VARIATIONAL GRAPH CONVOLUTIONAL NETWORKS FOR DYNAMIC GRAPH REPRESENTATION LEARNING,” IEEE Access, 2024, doi: https://doi.org/10.1109/ACCESS.2024.3483839.
  16. M. Zhao, C. Taal, S. Baggerohr, and O. Fink, “GRAPH NEURAL NETWORKS FOR VIRTUAL SENSING IN COMPLEX SYSTEMS: ADDRESSING HETEROGENEOUS TEMPORAL DYNAMICS,” 2025, doi: https://doi.org/10.2139/ssrn.4941745.
  17. A. T. Wasi, M. S. Islam, A. R. Akib, and M. M. Bappy, “GRAPH NEURAL NETWORKS IN SUPPLY CHAIN ANALYTICS AND OPTIMIZATION: CONCEPTS, PERSPECTIVES, DATASET AND BENCHMARKS,” Nov. 2024, [Online]. Available: http://arxiv.org/abs/2411.08550
  18. K. F. Mojdehi, B. Amiri, and A. Haddadi, “A NOVEL HYBRID MODEL FOR CREDIT RISK ASSESSMENT OF SUPPLY CHAIN FINANCE BASED ON TOPOLOGICAL DATA ANALYSIS AND GRAPH NEURAL NETWORK,” 2025.doi: https://doi.org/10.1109/ACCESS.2025.3528373
  19. D. Vallarino, “DYNAMIC PORTFOLIO REBALANCING: A HYBRID NEW MODEL USING GNNS AND PATHFINDING FOR COST EFFICIENCY,” 2024.
  20. M. S. Sonani, A. Badii, and A. Moin, “STOCK PRICE PREDICTION USING A HYBRID LSTM-GNN MODEL: INTEGRATING TIME-SERIES AND GRAPH-BASED ANALYSIS,” Feb. 2025, [Online]. Available: http://arxiv.org/abs/2502.15813
  21. S. Caton, S. Malisetty, and C. Haas, “IMPACT OF IMPUTATION STRATEGIES ON FAIRNESS IN MACHINE LEARNING,” Journal of Artificial Intelligence Research, vol. 74, pp. 1011–1035, 2022, doi: https://doi.org/10.1613/jair.1.13197.
  22. H. Bichri, A. Chergui, and M. Hain, “INVESTIGATING THE IMPACT OF TRAIN / TEST SPLIT RATIO ON THE PERFORMANCE OF PRE-TRAINED MODELS WITH CUSTOM DATASETS,” 2024. [Online]. Available: https://doi.org/10.14569/IJACSA.2024.0150235
  23. W. L. Hamilton, R. Ying, and J. Leskovec, “INDUCTIVE REPRESENTATION LEARNING ON LARGE GRAPHS.”
  24. Q. Zhu, N. Ponomareva, J. Han, and B. Perozzi, “SHIFT-ROBUST GNNS: OVERCOMING THE LIMITATIONS OF LOCALIZED GRAPH TRAINING DATA,” 2021. [Online]. Available: https://github.com/GentleZhu/Shift-Robust-GNNs.
  25. H. T. Kose, J. Nunez-Yanez, R. Piechocki, and J. Pope, “A SURVEY OF COMPUTATIONALLY EFFICIENT GRAPH NEURAL NETWORKS FOR RECONFIGURABLE SYSTEMS,” Information (Switzerland), vol. 15, no. 7, Jul. 2024, doi: https://doi.org/10.3390/info15070377.
  26. M. S. M. Bhuiyan et al., “DEEP LEARNING FOR ALGORITHMIC TRADING: A SYSTEMATIC REVIEW OF PREDICTIVE MODELS AND OPTIMIZATION STRATEGIES,” Jul. 01, 2025, Elsevier B.V. doi: https://doi.org/10.1016/j.array.2025.100390.