Unveiling high-dimensional time-varying extreme risk spillovers: AI-driven warning signals in the global energy market

Xu, Xin, Wang, Yizhi and Xie, Qichang 2026. Unveiling high-dimensional time-varying extreme risk spillovers: AI-driven warning signals in the global energy market. European Journal of Finance Item availability restricted.

	PDF - Accepted Post-Print Version Restricted to Repository staff only Download (7MB)
	PDF (Provisional file) - Accepted Post-Print Version Download (17kB)

Abstract

This paper investigates extreme risk spillovers in global energy markets using the enhanced highdimensional time-varying parameter vector autoregressive spillover (HD-TVP-VAR-SP) model. Weemploy the Long Short Term Memory (LSTM) model to develop an energy risk warning system,identifying key factors in risk contagion. Our findings reveal robust connectivity in global energymarket risks, characterized by high-dimensional complex networks with marked temporal variations.The Americas region emerges as the leading contributor to systemic risk shocks, primarily throughpositive spillovers in its energy markets. The LSTM model demonstrates superior extreme riskprediction compared to other machine learning models like Gradient Boosting Machines, RandomForest, and Decision Trees. The oil market is identified as a critical driver of risk contagion in theenergy sector. These insights provide valuable guidance for effectively identifying and managingglobal energy market risks and enhancing risk warning systems.

Item Type:	Article
Status:	In Press
Schools:	Schools > Business (Including Economics)
Subjects:	H Social Sciences > HG Finance
Publisher:	Taylor and Francis Group
ISSN:	1351-847X
Date of First Compliant Deposit:	25 February 2026
Date of Acceptance:	25 February 2026
Last Modified:	26 Feb 2026 09:45
URI:	https://orca.cardiff.ac.uk/id/eprint/185303

Actions (repository staff only)

Edit Item