Stratify: Unifying Multi-Step Forecasting Strategies
This work addresses the problem of ad-hoc strategy selection in multi-step forecasting for practitioners, offering a comprehensive benchmarking tool, though it is incremental in unifying and extending existing methods.
The authors tackled the lack of a unified framework for selecting multi-step forecasting strategies by proposing Stratify, a parameterized framework that unifies existing strategies and introduces novel ones, which improved performance in over 84% of experiments across 18 datasets and various forecast horizons.
A key aspect of temporal domains is the ability to make predictions multiple time steps into the future, a process known as multi-step forecasting (MSF). At the core of this process is selecting a forecasting strategy, however, with no existing frameworks to map out the space of strategies, practitioners are left with ad-hoc methods for strategy selection. In this work, we propose Stratify, a parameterised framework that addresses multi-step forecasting, unifying existing strategies and introducing novel, improved strategies. We evaluate Stratify on 18 benchmark datasets, five function classes, and short to long forecast horizons (10, 20, 40, 80). In over 84% of 1080 experiments, novel strategies in Stratify improved performance compared to all existing ones. Importantly, we find that no single strategy consistently outperforms others in all task settings, highlighting the need for practitioners explore the Stratify space to carefully search and select forecasting strategies based on task-specific requirements. Our results are the most comprehensive benchmarking of known and novel forecasting strategies. We make code available to reproduce our results.