MSATE-Net: A Multi-Scale Attention-Enhanced Bidirectional Temporal Network for Stock Index Forecasting
Symmetry · 19.08.2026 · 18 (8) · 1398
DOI: 10.3390/sym18081398 ↗Kurz gefasst
Fachartikel in der Zeitschrift Symmetry, online erschienen am 19.08.2026. Verfasst von Taoyin Wang und 4 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This study proposes MSATE-Net for next-day stock index forecasting. The model combines parallel one-dimensional convolutions with receptive fields of 3, 7, and 15 trading days, a bidirectional LSTM operating entirely inside a historical lookback window, sample-dependent temporal attention, and a residual regularized prediction head. Here, “bidirectional” denotes paired processing of the same observed window; it does not assert time-reversal invariance of financial prices or access to observations after the forecast origin. The globally learned attention temperature controls overall selectivity and is not described as a regime-specific adaptive parameter. Experiments use S&P 500, CSI 300, and Nikkei 225 data; persistence and drift benchmarks; recent forecasting architectures; five-seed uncertainty estimates; expanding-window tests; return and directional metrics; and Diebold–Mariano comparisons. The revised evidence supports lower price-level errors, while directional and significance results are mixed across markets. Because a separate model is fitted in each market, the findings establish cross-market consistency rather than transfer learning.
Zitieren
APA
Wang, T., Cheng, Y., Tang, Z., Shan, Y., & Wang, H. (2026). MSATE-Net: A Multi-Scale Attention-Enhanced Bidirectional Temporal Network for Stock Index Forecasting. Symmetry, 18(8), 1398. https://doi.org/10.3390/sym18081398
Vancouver
Wang T, Cheng Y, Tang Z, Shan Y, Wang H. MSATE-Net: A Multi-Scale Attention-Enhanced Bidirectional Temporal Network for Stock Index Forecasting. Symmetry. 2026;18(8):1398. doi:10.3390/sym18081398
BibTeX
@article{Wang2026,
author = {Wang, Taoyin and Cheng, Yiyuan and Tang, Zihao and Shan, Yahui and Wang, Hao},
title = {MSATE-Net: A Multi-Scale Attention-Enhanced Bidirectional Temporal Network for Stock Index Forecasting},
journal = {Symmetry},
year = {2026},
volume = {18},
number = {8},
pages = {1398},
doi = {10.3390/sym18081398}
}
EUVIMED