A convolutional framework for detecting event-driven dynamics in energy price series
Abstract
This paper develops a general convolutional neural network (CNN) framework for detecting heterogeneous event-driven dynamics in univariate time series windows. We show that the induced CNN class exactly represents classifiers based on range, maximum drawup, maximum drawdown and slope change, and uniformly approximates realised volatility and autoregressive explosiveness on compact domains. We further establish error bounds for representative rules in finite samples and an oracle inequality for learning across them. Simulations show that the proposed model can match or outperform classifiers based on individual statistics as the training sample grows. In an application to six daily energy price series, a hierarchical CNN distinguishes event windows and event families. Applied without retraining to observations withheld after 20 February 2026, the fitted model identifies predominantly geopolitical dynamics in several oil and refined product series around the outbreak of the 2026 Iran war, while distinguishing a contemporaneous natural gas spike associated with weather.
Related
- Hankel-Koopman Finite-Horizon Energy Decomposition of Coupled Experimental Data: A Three-Phase Data-Driven Twin Forecasting Framework
- An Energy-Driven Framework for Privacy-Aware Synthetic Data Generation
- Stochastic dynamics generation of directed percolation using a two-channel convolutional neural network
- Initial condition recovery in nonlinear damped viscous photoacoustic tomography using a convolutional neural network-guided gradient-free optimization framework
- Dynamical and stationary non-equilibrium fluctuations for a boundary-driven exclusion process with energy
BibTeX
@misc{xu2026convolutional,
title = {{A convolutional framework for detecting event-driven dynamics in energy price series}},
author = {Caixia Xu and Piotr Fryzlewicz},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.00402},
eprint = {2609.00402},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.00402},
}
RIS
TY - UNPB
TI - A convolutional framework for detecting event-driven dynamics in energy price series
AU - Caixia Xu
AU - Piotr Fryzlewicz
PY - 2026
DA - 2026/09/05
PB - arXiv
DO - 10.48550/arxiv.2609.00402
UR - https://arxiv.org/abs/2609.00402
AB - This paper develops a general convolutional neural network (CNN) framework for detecting heterogeneous event-driven dynamics in univariate time series windows. We show that the induced CNN class exactly represents classifiers based on range, maximum drawup, maximum drawdown and slope change, and uniformly approximates realised volatility and autoregressive explosiveness on compact domains. We further establish error bounds for representative rules in finite samples and an oracle inequality for learning across them. Simulations show that the proposed model can match or outperform classifiers based on individual statistics as the training sample grows. In an application to six daily energy price series, a hierarchical CNN distinguishes event windows and event families. Applied without retraining to observations withheld after 20 February 2026, the fitted model identifies predominantly geopolitical dynamics in several oil and refined product series around the outbreak of the 2026 Iran war, while distinguishing a contemporaneous natural gas spike associated with weather.
ER -