<ul><li>Traditional time-series forecasting often focuses only on minimizing prediction errors, ignoring the specific requirements of real-world applications that employ them.</li><li>A new training methodology is presented in this paper which allows a forecasting model to dynamically adjust its focus based on the importance of forecast ranges specified by the end application.</li><li>Unlike previous methods, this approach breaks down predictions over the entire signal range into smaller segments, which are then dynamically weighted and combined to produce accurate forecasts.</li><li>Testing on standard datasets, including a new dataset from wireless communication, showed that this method not only improves prediction accuracy but also enhances the performance of end applications using the forecasting model.</li></ul>

Goal-Oriented Time-Series Forecasting: Foundation Framework Design

Discover more