EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Regime-Dependent Graph Neural Networks for Enhanced Volatility Prediction in Financial Markets

Pulikandala Nithish Kumar, Nneka Umeorah, Alex Alochukwu

Mathematics · 13.01.2026 · 14 (2) · 289

DOI: 10.3390/math14020289 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 13.01.2026. Verfasst von Pulikandala Nithish Kumar und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate volatility forecasting is essential for risk management in increasingly interconnected financial markets. Traditional econometric models capture volatility clustering but struggle to model nonlinear cross-market spillovers. This study proposes a Temporal Graph Attention Network (TemporalGAT) for multi-horizon volatility forecasting, integrating LSTM-based temporal encoding with graph convolutional and attention layers to jointly model volatility persistence and inter-market dependencies. Market linkages are constructed using the Diebold–Yilmaz volatility spillover index, providing an economically interpretable representation of directional shock transmission. Using daily data from major global equity indices, the model is evaluated against econometric, machine learning, and graph-based benchmarks across multiple forecast horizons. Performance is assessed using MSE, R2, MAFE, and MAPE, with statistical significance validated via Diebold–Mariano tests and bootstrap confidence intervals. The study further conducts a strict expanding-window robustness test, comparing fixed and dynamically re-estimated spillover graphs in a fully out-of-sample setting. Sensitivity and scenario analyses confirm robustness across hyperparameter configurations and market regimes, while results show no systematic gains from dynamic graph updating over a fixed spillover network.

Zitieren

APA

Kumar, P. N., Umeorah, N., & Alochukwu, A. (2026). Regime-Dependent Graph Neural Networks for Enhanced Volatility Prediction in Financial Markets. Mathematics, 14(2), 289. https://doi.org/10.3390/math14020289

Vancouver

Kumar PN, Umeorah N, Alochukwu A. Regime-Dependent Graph Neural Networks for Enhanced Volatility Prediction in Financial Markets. Mathematics. 2026;14(2):289. doi:10.3390/math14020289

BibTeX
@article{Kumar2026,
  author = {Kumar, Pulikandala Nithish and Umeorah, Nneka and Alochukwu, Alex},
  title = {Regime-Dependent Graph Neural Networks for Enhanced Volatility Prediction in Financial Markets},
  journal = {Mathematics},
  year = {2026},
  volume = {14},
  number = {2},
  pages = {289},
  doi = {10.3390/math14020289}
}
Kostenlos starten →