Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping
This work provides insights into simplifying forecasting models, potentially reducing computational costs for practitioners, but it is incremental as it builds on prior demonstrations of linear methods.
The paper investigates the effectiveness of linear mapping for long-term time series forecasting, finding that a single linear layer with techniques like RevIN and CI achieves competitive performance by capturing periodic features robustly across channels.
Long-term time series forecasting has gained significant attention in recent years. While there are various specialized designs for capturing temporal dependency, previous studies have demonstrated that a single linear layer can achieve competitive forecasting performance compared to other complex architectures. In this paper, we thoroughly investigate the intrinsic effectiveness of recent approaches and make three key observations: 1) linear mapping is critical to prior long-term time series forecasting efforts; 2) RevIN (reversible normalization) and CI (Channel Independent) play a vital role in improving overall forecasting performance; and 3) linear mapping can effectively capture periodic features in time series and has robustness for different periods across channels when increasing the input horizon. We provide theoretical and experimental explanations to support our findings and also discuss the limitations and future works. Our framework's code is available at \url{https://github.com/plumprc/RTSF}.