Multi-Scale Temporal Neural Network for Stock Trend Prediction Enhanced by Temporal Hyepredge Learning

Song, Lingyun; Li, Haodong; Chen, Siyu; Gan, Xinbiao; Shi, Binze; Ma, Jie; Pan, Yudai; Wang, Xiaoqi; Shang, Xuequn

doi:10.24963/ijcai.2025/364

Multi-Scale Temporal Neural Network for Stock Trend Prediction Enhanced by Temporal Hyepredge Learning

Lingyun Song, Haodong Li, Siyu Chen, Xinbiao Gan, Binze Shi, Jie Ma, Yudai Pan, Xiaoqi Wang, Xuequn Shang

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 3272-3280.

https://doi.org/10.24963/ijcai.2025/364

Keywords

Machine Learning: ML: Relational learning
Data Mining: DM: Applications
Machine Learning: ML: Deep learning architectures
Machine Learning: ML: Classification

Abstract

Existing research in Stock Trend Prediction (STP) focuses on temporal features extracted from a temporal sequence of stock data with a look-back window, which frequently leads to the omission of important periodic patterns, such as weekly and monthly variations in stock prices. Furthermore, these methods examine stocks individually, ignoring the temporal variation patterns among stocks that share higher-order relationships, like those within the same industry. These relationships typically provide contextual insights into market investments influencing stock price fluctuations. To tackle these issues, we propose a Multi-Scale Temporal Neural Network (MSTNN) framework tailored for STP. This architecture explores the periodic fluctuation behaviors of individual stocks through an innovative 3D convolutional neural network, alongside examining temporal variation patterns of stocks linked to specific industries via a temporal hypergraph attention mechanism. Empirical results from two real-world benchmark datasets show that MSTNN significantly outperforms prior state-of-the-art STP methods. The code of our MSTNN is available at https://github.com/sunlitsong/MSTNN.

Lingyun Song, Haodong Li, Siyu Chen, Xinbiao Gan, Binze Shi, Jie Ma, Yudai Pan, Xiaoqi Wang, and Xuequn Shang. 2025. Multi-Scale Temporal Neural Network for Stock Trend Prediction Enhanced by Temporal Hyepredge Learning. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 3272–3280. https://doi.org/10.24963/ijcai.2025/364

@inproceedings{ijcai2025p364,
  title     = {Multi-Scale Temporal Neural Network for Stock Trend Prediction Enhanced by Temporal Hyepredge Learning},
  author    = {Song, Lingyun and Li, Haodong and Chen, Siyu and Gan, Xinbiao and Shi, Binze and Ma, Jie and Pan, Yudai and Wang, Xiaoqi and Shang, Xuequn},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {3272--3280},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/364},
  url       = {https://doi.org/10.24963/ijcai.2025/364},
}

TY  - CPAPER
TI  - Multi-Scale Temporal Neural Network for Stock Trend Prediction Enhanced by Temporal Hyepredge Learning
AU  - Song, Lingyun
AU  - Li, Haodong
AU  - Chen, Siyu
AU  - Gan, Xinbiao
AU  - Shi, Binze
AU  - Ma, Jie
AU  - Pan, Yudai
AU  - Wang, Xiaoqi
AU  - Shang, Xuequn
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 3272
EP  - 3280
DO  - 10.24963/ijcai.2025/364
UR  - https://doi.org/10.24963/ijcai.2025/364
ER  -