Metraipolis › archive › dc_526bc4769fc9

A convolutional framework for detecting event-driven dynamics in energy price series — arXiv:2609.00402

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00402
License (as archived)
CC0-1.0
Archived
2026-10-17T06:52:30.835Z
SHA-256 of the archived text
c3ddcec92ac4615ae5d7561470abf8a33ffa80341244403b6807fbd304214881
Stable URL of this page
https://metraipolis.com/documento/dc_526bc4769fc9

How to cite

A convolutional framework for detecting event-driven dynamics in energy price series — arXiv:2609.00402 — arXiv (en), https://arxiv.org/abs/2609.00402 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_526bc4769fc9 (Metraipolis archive dc_526bc4769fc9, sha256 c3ddcec92ac4615ae5d7561470abf8a33ffa80341244403b6807fbd304214881)
BibTeX
@misc{dc526bc4769fc9,
  title = {A convolutional framework for detecting event-driven dynamics in energy price series — arXiv:2609.00402},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00402},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_526bc4769fc9; sha256 c3ddcec92ac4615ae5d7561470abf8a33ffa80341244403b6807fbd304214881},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00402. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Methodology (stat.ME).
Pagina del lavoro: https://arxiv.org/abs/2609.00402 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T06:41:55.889Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).