Goal-Oriented Time-Series Forecasting: Foundation Framework Design
This addresses the need for better integration of forecasting with decision-making in real-world systems, offering a flexible framework for domain-specific applications.
The paper tackles the problem of conventional time-series forecasting ignoring varying importance of forecast ranges in applications by proposing a training methodology that adapts focus to application-specific regions at inference time without retraining, resulting in improved forecast accuracy and downstream task performance on benchmarks and a new dataset.
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.