Pré-Publication, Document De Travail Année : 2025

Sliding-Window Signatures for Time Series: Application to Electricity Demand Forecasting

Résumé

Nonlinear and delayed effects of covariates often render time series forecasting challenging. To this end, we propose a novel forecasting framework based on ridge regression with signature features calculated on sliding windows. These features capture complex temporal dynamics without relying on learned or hand-crafted representations. Focusing on the discrete-time setting, we establish theoretical guarantees, namely universality of approximation and stationarity of signatures. We introduce an efficient sequential algorithm for computing signatures on sliding windows. The method is evaluated on both synthetic and real electricity demand data. Results show that signature features effectively encode temporal and nonlinear dependencies, yielding accurate forecasts competitive with those based on expert knowledge.

Fichier principal
Vignette du fichier
Sliding_Window_Signatures_Preprint_final (1).pdf (915.5 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05308724 , version 1 (13-10-2025)

Licence

Identifiants

  • HAL Id : hal-05308724 , version 1

Citer

Nina Drobac, Margaux Brégère, Joseph de Vilmarest, Olivier Wintenberger. Sliding-Window Signatures for Time Series: Application to Electricity Demand Forecasting. 2025. ⟨hal-05308724⟩
422 Consultations
144 Téléchargements

Partager

  • More