EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EMAT: Enhanced Multi-Aspect Attention Transformer for Financial Time Series Forecasting

Yingjun Chen, Wenfeng Shen, Han Liu iD, Xiaolin Cao

Entropy · 01.10.2025 · 27 (10) · 1029

DOI: 10.3390/e27101029 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 01.10.2025. Verfasst von Yingjun Chen und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer and Information Engineering, Shanghai Polytechnic University, Shanghai 201209, China. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: AI-Driven Reform of Scientific Research Paradigms and Discipline Leapfrogging Initiative.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Financial time series prediction remains a challenging task due to the inherent non-stationarity, noise, and complex temporal dependencies present in market data. Traditional forecasting methods often fail to capture the multifaceted nature of financial markets, where temporal proximity, trend dynamics, and volatility patterns simultaneously influence price movements. To address these limitations, this paper proposes the Enhanced Multi-Aspect Transformer (EMAT), a novel deep learning architecture specifically designed for stock market prediction. EMAT incorporates a Multi-Aspect Attention Mechanism that simultaneously captures temporal decay patterns, trend dynamics, and volatility regimes through specialized attention components. The model employs an encoder–decoder architecture with enhanced feed-forward networks utilizing SwiGLU activation, enabling superior modeling of complex non-linear relationships. Furthermore, we introduce a comprehensive multi-objective loss function that balances point-wise prediction accuracy with volatility consistency. Extensive experiments on multiple stock market datasets demonstrate that EMAT consistently outperforms a wide range of state-of-the-art baseline models, including various recurrent, hybrid, and Transformer architectures. Our ablation studies further validate the design, confirming that each component of the Multi-Aspect Attention Mechanism makes a critical and quantifiable contribution to the model’s predictive power. The proposed architecture’s ability to simultaneously model these distinct financial characteristics makes it a particularly effective and robust tool for financial forecasting, offering significant improvements in accuracy compared to existing approaches.

Schlagwörter

Stichwörter der Autor:innen

Multi-Aspect Attention Mechanismfinancial time series predictionstock market forecastingtransformer modelvolatility-aware modeling

Autor:innen und Institutionen

  • School of Computer and Information Engineering, Shanghai Polytechnic University, Shanghai 201209, China.

ORCID-Profile: Han Liu

Förderung

  • AI-Driven Reform of Scientific Research Paradigms and Discipline Leapfrogging Initiative

Zitieren

APA

Chen, Y., Shen, W., Liu, H., & Cao, X. (2025). EMAT: Enhanced Multi-Aspect Attention Transformer for Financial Time Series Forecasting. Entropy, 27(10), 1029. https://doi.org/10.3390/e27101029

Vancouver

Chen Y, Shen W, Liu H, Cao X. EMAT: Enhanced Multi-Aspect Attention Transformer for Financial Time Series Forecasting. Entropy. 2025;27(10):1029. doi:10.3390/e27101029

BibTeX
@article{Chen2025,
  author = {Chen, Yingjun and Shen, Wenfeng and Liu, Han and Cao, Xiaolin},
  title = {EMAT: Enhanced Multi-Aspect Attention Transformer for Financial Time Series Forecasting},
  journal = {Entropy},
  year = {2025},
  volume = {27},
  number = {10},
  pages = {1029},
  doi = {10.3390/e27101029}
}
Kostenlos starten →