A Decomposition Modeling Framework for Seasonal Time-Series Forecasting
This work addresses the problem of accurate seasonal time-series forecasting for domains like finance or climate, but it is incremental as it builds on existing decomposition and network methods.
The paper tackles the challenge of forecasting seasonal time series with long-term dependencies by introducing the Multi-scale Seasonal Decomposition Model (MSSD), which decomposes time series into Ascending, Peak, and Descending components and uses a multi-scale network to capture peak fluctuations, resulting in a 10% error reduction compared to baselines in short-term and long-term forecasting tasks.
Seasonal time series exhibit intricate long-term dependencies, posing a significant challenge for accurate future prediction. This paper introduces the Multi-scale Seasonal Decomposition Model (MSSD) for seasonal time-series forecasting. Initially, leveraging the inherent periodicity of seasonal time series, we decompose the univariate time series into three primary components: Ascending, Peak, and Descending. This decomposition approach enhances the capture of periodic features. By addressing the limitations of existing time-series modeling methods, particularly in modeling the Peak component, this research proposes a multi-scale network structure designed to effectively capture various potential peak fluctuation patterns in the Peak component. This study integrates Conv2d and Temporal Convolutional Networks to concurrently capture global and local features. Furthermore, we incorporate multi-scale reshaping to augment the modeling capacity for peak fluctuation patterns. The proposed methodology undergoes validation using three publicly accessible seasonal datasets. Notably, in both short-term and long-term fore-casting tasks, our approach exhibits a 10$\%$ reduction in error compared to the baseline models.