Time-Varying Stochastic Graph Learning for Probabilistic Financial Forecasting

Article Sidebar

PDF
DOI: https://doi.org/10.28924/2291-8639-24-2026-363
Published: Oct 26, 2026
Cite as:
Le Binh Trung, Duong Kim Ngoc, Le Vu Truong, Le Thi Kim Anh, Time-Varying Stochastic Graph Learning for Probabilistic Financial Forecasting, Int. J. Anal. Appl., 24 (2026), 363.

Main Article Content

Le Binh Trung, Duong Kim Ngoc, Le Vu Truong, Le Thi Kim Anh

Abstract

Financial forecasting involves both time-varying interactions among market variables and substantial uncertainty, yet these two features are often modeled separately or through fixed relational structures. This study develops a time-varying stochastic graph framework that jointly learns dynamic financial connectivity and probabilistic forecasts. The empirical application uses 2,544 daily observations from January 2015 to July 2026 for the Straits Times Index (STI), USD/SGD exchange rate, VIX, and S&P 500. A state-dependent stochastic graph is learned from the observed financial variables, and the resulting graph representations are processed by a long short-term memory network to estimate the conditional mean and standard deviation of next-day STI returns. Out-of-sample results show only marginal improvements in point forecasting over a random-walk benchmark, with directional accuracy of 50.8%. In contrast, the model produces time-varying graph connectivity and reasonably calibrated predictive intervals, with empirical coverage of 84.6% and 93.7% for the nominal 80% and 95% intervals, respectively.

Article Details

References

  1. D.P. Gandhmal, K. Kumar, Systematic Analysis and Review of Stock Market Prediction Techniques, Comput. Sci. Rev. 34 (2019), 100190. https://doi.org/10.1016/j.cosrev.2019.08.001.
  2. H. Rezaei, H. Faaljou, G. Mansourfar, Stock Price Prediction Using Deep Learning and Frequency Decomposition, Expert Syst. Appl. 169 (2021), 114332. https://doi.org/10.1016/j.eswa.2020.114332.
  3. C. Zhang, Q. Lan, X. Mi, Z. Zhou, C. Ma, et al., A Denoising Method Based on the Nonlinear Relationship between the Target Variable and Input Features, Expert Syst. Appl. 218 (2023), 119585. https://doi.org/10.1016/j.eswa.2023.119585.
  4. H. Yu, J. Dong, B. Li, Economic Insight through an Optimized Deep Learning Model for Stock Market Prediction Regarding Dow Jones Industrial Average Index, Expert Syst. Appl. 291 (2025), 128473. https://doi.org/10.1016/j.eswa.2025.128473.
  5. Y. Huang, C. Yang, Enhancing Stock Price Forecasting with a Modular Deep Learning Framework Incorporating Plug-and-Play Transformer Variants, Expert Syst. Appl. 315 (2026), 131572. https://doi.org/10.1016/j.eswa.2026.131572.
  6. T. Fischer, C. Krauss, Deep Learning with Long Short-Term Memory Networks for Financial Market Predictions, Eur. J. Oper. Res. 270 (2018), 654–669. https://doi.org/10.1016/j.ejor.2017.11.054.
  7. K. Olorunnimbe, H. Viktor, Deep Learning in the Stock Market—a Systematic Survey of Practice, Backtesting, and Applications, Artif. Intell. Rev. 56 (2023), 2057–2109. https://doi.org/10.1007/s10462-022-10226-0.
  8. T.T. Huynh, B.T. Khoa, N.T.K. An, Return Reversal in Portfolios Optimized under Exchange Rate Risk: Evidence from Vietnam’s HNX Market, Int. J. Anal. Appl. 23 (2025), 237. https://doi.org/10.28924/2291-8639-23-2025-237.
  9. D. Cheng, F. Yang, S. Xiang, J. Liu, Financial Time Series Forecasting with Multi-Modality Graph Neural Network, Pattern Recognit. 121 (2022), 108218. https://doi.org/10.1016/j.patcog.2021.108218.
  10. F. Feng, X. He, X. Wang, C. Luo, Y. Liu, et al., Temporal Relational Ranking for Stock Prediction, ACM Trans. Inf. Syst. 37 (2019), 1–30. https://doi.org/10.1145/3309547.
  11. C. Xu, H. Huang, X. Ying, J. Gao, Z. Li, et al., HGNN: Hierarchical Graph Neural Network for Predicting the Classification of Price-Limit-Hitting Stocks, Inf. Sci. 607 (2022), 783–798. https://doi.org/10.1016/j.ins.2022.06.010.
  12. S. Saha, J. Gao, R. Gerlach, A Survey of the Application of Graph-Based Approaches in Stock Market Analysis and Prediction, Int. J. Data Sci. Anal. 14 (2022), 1–15. https://doi.org/10.1007/s41060-021-00306-9.
  13. Y. Wang, Y. Qu, Z. Chen, Review of Graph Construction and Graph Learning in Stock Price Prediction, Procedia Comput. Sci. 214 (2022), 771–778. https://doi.org/10.1016/j.procs.2022.11.240.
  14. R. Liu, H. Liu, H. Huang, B. Song, Q. Wu, Multimodal Multiscale Dynamic Graph Convolution Networks for Stock Price Prediction, Pattern Recognit. 149 (2024), 110211. https://doi.org/10.1016/j.patcog.2023.110211.
  15. H. Qian, H. Zhou, Q. Zhao, H. Chen, H. Yao, et al., MDGNN: Multi-Relational Dynamic Graph Neural Network for Comprehensive and Dynamic Stock Investment Prediction, Proc. AAAI Conf. Artif. Intell. 38 (2024), 14642–14650. https://doi.org/10.1609/aaai.v38i13.29381.
  16. D. Daiya, M. Yadav, H.S. Rao, Diffstock: Probabilistic Relational Stock Market Predictions Using Diffusion Models, in: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2024, pp. 7335–7339. https://doi.org/10.1109/ICASSP48485.2024.10446690.
  17. T.T. Huynh, B.T. Khoa, Financial Bubble Detection Using GSADF and LSTM-RNN Model: Evidence from Emerging Markets, Int. J. Anal. Appl. 23 (2025), 150. https://doi.org/10.28924/2291-8639-23-2025-150.
  18. B.T. Khoa, T.T. Huynh, Long Short-Term Memory Recurrent Neural Network for Predicting the Return of Rate Underframe the Fama-French 5 Factor, Discret. Dyn. Nat. Soc. 2022 (2022), 3936122. https://doi.org/10.1155/2022/3936122.
  19. N.T.K. An, Modeling and Forecasting Excess Market Returns Using a Two-Factor CIR Model, Int. J. Anal. Appl. 24 (2026), 180. https://doi.org/10.28924/2291-8639-24-2026-180.
  20. T.T. Huynh, N.T.K. An, Dataset on Composite Efficiency Indices for ASEAN Foreign Exchange Markets, Data Brief 67 (2026), 112913. https://doi.org/10.1016/j.dib.2026.112913.