FATE-Net: An Optimization-Enhanced Attention-Driven Temporal Evolution Framework for Stock Price Forecasting
Mathematics · 12.03.2026 · 14 (6) · 964
DOI: 10.3390/math14060964 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 12.03.2026. Verfasst von Zhizhe Lin und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Philosophy and Social Sciences Planning Project of Zhejiang Province, Hainan Provincial Natural Science Foundation of China.
Abstract (Originalsprache)
Stock price forecasting remains challenging due to the nonlinear, volatile, multi-scale dynamics of financial time series. This study addresses two core limitations of existing models: incomplete capture of full-spectrum multi-scale temporal dependencies and severe hyperparameter sensitivity caused by inefficient manual tuning. To solve these issues, we propose FATE-Net, an optimization-enhanced attention-driven forecasting framework. FATE-Net first integrates LSTM-based local encoding and Transformer-based global refinement to model multi-scale temporal dependencies. To address hyperparameter sensitivity, we embed a multi-objective particle swarm optimization (MOPSO) strategy, which formulates hyperparameter configuration as a dual-objective problem minimizing MAPE and RMSE, automatically exploring the hyperparameter space to find optimal configurations and enhance model generalization. Experiments on BYD stock data show that FATE-Net achieves state-of-the-art performance, with an MAE of 1.051, RMSE of 1.435, MAPE of 0.37%, and R2 of 0.997, verifying our framework’s effectiveness.
Förderung
- National Natural Science Foundation of China
- Philosophy and Social Sciences Planning Project of Zhejiang Province
- Hainan Provincial Natural Science Foundation of China
- Guangdong Basic and Applied Basic Research Foundation
- Guangxi Natural Science Foundation
- Hainan Province Higher Education Teaching Reform Project
Zitieren
APA
Lin, Z., Li, P., Zhao, Z., Wang, F., Zhou, T., & Cao, C. (2026). FATE-Net: An Optimization-Enhanced Attention-Driven Temporal Evolution Framework for Stock Price Forecasting. Mathematics, 14(6), 964. https://doi.org/10.3390/math14060964
Vancouver
Lin Z, Li P, Zhao Z, Wang F, Zhou T, Cao C. FATE-Net: An Optimization-Enhanced Attention-Driven Temporal Evolution Framework for Stock Price Forecasting. Mathematics. 2026;14(6):964. doi:10.3390/math14060964
BibTeX
@article{Lin2026,
author = {Lin, Zhizhe and Li, Pengbo and Zhao, Zhibo and Wang, Fei and Zhou, Teng and Cao, Chunjie},
title = {FATE-Net: An Optimization-Enhanced Attention-Driven Temporal Evolution Framework for Stock Price Forecasting},
journal = {Mathematics},
year = {2026},
volume = {14},
number = {6},
pages = {964},
doi = {10.3390/math14060964}
}
EUVIMED