Spatiotemporal Fusion for Stock Prediction via Hypergraph Attention Gated Recurrent Units
Entropy · 03.05.2026 · 28 (5) · 517
DOI: 10.3390/e28050517 ↗Kurz gefasst
Fachartikel in der Zeitschrift Entropy, online erschienen am 03.05.2026. Verfasst von Xinmei Cao und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Statistics and Data Science, Lanzhou University of Finance and Economics, Lanzhou 730020, China. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Central Government Funds for Guiding Local Science and Technology Development.
Abstract (Originalsprache)
Stock prediction requires the joint modeling of temporal dynamics and cross-stock dependence. Existing graph-based and hypergraph-based forecasting methods often process spatial relation modeling and temporal evolution in separate stages, which may weaken the interaction between relational information and recurrent state updating. This study proposes a Recurrent Spatiotemporal Hypergraph Attention Gated Recurrent Unit model for stock forecasting, in which hypergraph-based higher order dependence and temporal dynamics are integrated within each recurrent update. The hypergraph is constructed offline from heterogeneous financial features through Tucker decomposition, similarity estimation, and Top-K sparsification, and is then used as a structured relational prior during forecasting. Experiments on CSI 300 constituent stocks from January 2014 to October 2024 show that RST-HGA-GRU achieves the best overall performance across multiple evaluation metrics and forecasting horizons from 1 to 6 days. Ablation, sensitivity, back testing, and multi-horizon Diebold–Mariano tests further support the effectiveness and robustness of the proposed framework. These results demonstrate that recurrent spatiotemporal fusion with hypergraph-based higher-order relation modeling is effective for stock price forecasting.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Statistics and Data Science, Lanzhou University of Finance and Economics, Lanzhou 730020, China.
- Key Laboratory of Digital Economy and Social Computing Science of Gansu, Lanzhou 730020, China.
ORCID-Profile: Chonghui Qian
Förderung
- Central Government Funds for Guiding Local Science and Technology Development
Zitieren
APA
Cao, X., Qian, C., & Huang, H. (2026). Spatiotemporal Fusion for Stock Prediction via Hypergraph Attention Gated Recurrent Units. Entropy, 28(5), 517. https://doi.org/10.3390/e28050517
Vancouver
Cao X, Qian C, Huang H. Spatiotemporal Fusion for Stock Prediction via Hypergraph Attention Gated Recurrent Units. Entropy. 2026;28(5):517. doi:10.3390/e28050517
BibTeX
@article{Cao2026,
author = {Cao, Xinmei and Qian, Chonghui and Huang, Hengjun},
title = {Spatiotemporal Fusion for Stock Prediction via Hypergraph Attention Gated Recurrent Units},
journal = {Entropy},
year = {2026},
volume = {28},
number = {5},
pages = {517},
doi = {10.3390/e28050517}
}
EUVIMED