TCGformer: a temporal causal graph enhanced transformer model for multivariate financial time series forecasting
PeerJ Computer Science · 23.06.2026 · 12 · e3959
DOI: 10.7717/peerj-cs.3959 ↗Kurz gefasst
Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 23.06.2026. Verfasst von Sihua Tian und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Social Science Foundation of China, National Natural Science Foundation of China, Key Project of Philosophy and Social Science Research in Colleges and Universities of Jiangsu Province.
Abstract (Originalsprache)
State-of-the-art time series forecasting models, particularly Transformers, often fail to capture the time-varying causal structures that govern interactions among financial institutions, limiting their predictive accuracy in complex environments. This article introduces the Temporal Causal Graph-Enhanced Transformer (TCGformer), a novel causal knowledge-based intelligent system that integrates causal inference into deep learning for time series prediction. Our framework employs a three-stage pipeline: we first utilize Functional Data Analysis for robust preprocessing of noisy and irregular financial data; we then construct temporal causal graph using Variable-lag Granger Causality, a state-of-the-art causal inference method for observational causal discovery in time series, to model the evolving network of inter-institutional influence; finally, we seamlessly inject this externally grounded causal knowledge into a hierarchical Transformer architecture via our proposed Graph Neural Network (GNN)—empowered hybrid routing mechanism. We conduct extensive experiments on a real-world dataset. The results demonstrate that TCGformer consistently outperforms strong baselines, including Crossformer and Transformer, across multiple evaluation metrics. Ablation and robustness analysis reveals a key insight into the model’s operational strengths: its performance advantage is particularly pronounced in the medium-to-long-term forecasting horizons. This suggests that our knowledge-driven approach is effective at capturing the fundamental, structural market dynamics that are crucial for longer-range prediction. Furthermore, the more explainable temporal causal graphs provide valuable and interpretable insights into the shifting patterns of systemic risk. TCGformer represents a novel framework that synergistically fuses temporal causal knowledge into a Transformer-based forecasting architecture, bridging the gap between causal discovery and deep learning for intelligent decision-making in finance.
Förderung
- National Social Science Foundation of China
- National Natural Science Foundation of China
- Key Project of Philosophy and Social Science Research in Colleges and Universities of Jiangsu Province
- Jiangsu Province Social Science Fund Project
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Tian, S., & Li, S. (2026). TCGformer: a temporal causal graph enhanced transformer model for multivariate financial time series forecasting. PeerJ Computer Science, 12, e3959. https://doi.org/10.7717/peerj-cs.3959
Vancouver
Tian S, Li S. TCGformer: a temporal causal graph enhanced transformer model for multivariate financial time series forecasting. PeerJ Computer Science. 2026;12:e3959. doi:10.7717/peerj-cs.3959
BibTeX
@article{Tian2026,
author = {Tian, Sihua and Li, Shaofang},
title = {TCGformer: a temporal causal graph enhanced transformer model for multivariate financial time series forecasting},
journal = {PeerJ Computer Science},
year = {2026},
volume = {12},
pages = {e3959},
doi = {10.7717/peerj-cs.3959}
}
EUVIMED