Decompose and Conquer: Time Series Forecasting with Multiseasonal Trend Decomposition Using Loess

• Published in: Forecasting Vol. 5; no. 4; pp. 684 - 696
• Main Authors: Sohrabbeig, Amirhossein, Ardakanian, Omid, Musilek, Petr
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.12.2023
• Subjects: Accuracy; Analysis; Decomposition; Decomposition (Mathematics); Deep learning; Forecasting; Machine learning; Mathematical models; Mathematical research; Methods; multiseasonal; Multivariate analysis; Neural networks; Seasonal variations; Statistical models; Synthetic data; Time series; time series forecasting; Trends; Canada
• ISSN: 2571-9394; 2571-9394
• DOI: 10.3390/forecast5040037

Over the past few years, there has been growing attention to the Long-Term Time Series Forecasting task and solving its inherent challenges like the non-stationarity of the underlying distribution. Notably, most successful models in this area use decomposition during preprocessing. Yet, much of the recent research has focused on intricate forecasting techniques, often overlooking the critical role of decomposition, which we believe can significantly enhance the performance. Another overlooked aspect is the presence of multiseasonal components in many time series datasets. This study introduced a novel forecasting model that prioritizes multiseasonal trend decomposition, followed by a simple, yet effective forecasting approach. We submit that the right decomposition is paramount. The experimental results from both real-world and synthetic data underscore the efficacy of the proposed model, Decompose&Conquer, for all benchmarks with a great margin, around a 30–50% improvement in the error.