Loading...
Do simpler statistical methods perform better in multivariate long sequence time-series forecasting?
Li, Hao Shao, Jie Liao, Kewen Tang, Mingjian
Li, Hao
Shao, Jie
Liao, Kewen
Tang, Mingjian
Abstract
Long sequence time-series forecasting has become a central problem in multivariate time-series analysis due to its difficulty of consistently maintaining low prediction errors. Recent research has concentrated on developing large deep learning frameworks such as Informer and SCINet with remarkable results. However, these complex approaches were not benchmarked with simpler statistical methods and hence this part of the puzzle is missing for multivariate long sequence time-series forecasting (MLSTF). We investigate two simple statistical methods for MLSTF and provide analysis to indicate that linear regression owns a lower upper bound of error than deep learning methods and SNaive can act as an effective nonparametric method with unpredictable trends. Evaluations across six real-world datasets demonstrate that linear regression and SNaive are able to achieve state-of-the-art performance for MLSTF.
Keywords
time-series forecasting, deep learning, statistical methods
Date
2022
Type
Conference paper
Journal
Book
CIKM '22 : Proceedings of the 31st ACM International Conference on Information & Knowledge Management
Volume
Issue
Page Range
4168-4172
Article Number
ACU Department
Peter Faber Business School
Faculty of Law and Business
Faculty of Law and Business
Collections
Relation URI
Source URL
Event URL
Open Access Status
License
All rights reserved
File Access
Controlled