Goal-Oriented Time-Series Forecasting: Foundation Framework Design

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Fechete, Luca-Andrei, Sana, Mohamed, Ayed, Fadhel, Piovesan, Nicola, Li, Wenjie, De Domenico, Antonio, Salem, Tareq Si
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913990083346432
author Fechete, Luca-Andrei
Sana, Mohamed
Ayed, Fadhel
Piovesan, Nicola
Li, Wenjie
De Domenico, Antonio
Salem, Tareq Si
author_facet Fechete, Luca-Andrei
Sana, Mohamed
Ayed, Fadhel
Piovesan, Nicola
Li, Wenjie
De Domenico, Antonio
Salem, Tareq Si
contents Conventional time-series forecasting methods typically aim to minimize overall prediction error, without accounting for the varying importance of different forecast ranges in downstream applications. We propose a training methodology that enables forecasting models to adapt their focus to application-specific regions of interest at inference time, without retraining. The approach partitions the prediction space into fine-grained segments during training, which are dynamically reweighted and aggregated to emphasize the target range specified by the application. Unlike prior methods that predefine these ranges, our framework supports flexible, on-demand adjustments. Experiments on standard benchmarks and a newly collected wireless communication dataset demonstrate that our method not only improves forecast accuracy within regions of interest but also yields measurable gains in downstream task performance. These results highlight the potential for closer integration between predictive modeling and decision-making in real-world systems.
format Preprint
id arxiv_https___arxiv_org_abs_2504_17493
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Goal-Oriented Time-Series Forecasting: Foundation Framework Design
Fechete, Luca-Andrei
Sana, Mohamed
Ayed, Fadhel
Piovesan, Nicola
Li, Wenjie
De Domenico, Antonio
Salem, Tareq Si
Machine Learning
Artificial Intelligence
Conventional time-series forecasting methods typically aim to minimize overall prediction error, without accounting for the varying importance of different forecast ranges in downstream applications. We propose a training methodology that enables forecasting models to adapt their focus to application-specific regions of interest at inference time, without retraining. The approach partitions the prediction space into fine-grained segments during training, which are dynamically reweighted and aggregated to emphasize the target range specified by the application. Unlike prior methods that predefine these ranges, our framework supports flexible, on-demand adjustments. Experiments on standard benchmarks and a newly collected wireless communication dataset demonstrate that our method not only improves forecast accuracy within regions of interest but also yields measurable gains in downstream task performance. These results highlight the potential for closer integration between predictive modeling and decision-making in real-world systems.
title Goal-Oriented Time-Series Forecasting: Foundation Framework Design
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2504.17493