Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysis
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913549237878784 |
|---|---|
| author | Shao, Zezhi Wang, Fei Xu, Yongjun Wei, Wei Yu, Chengqing Zhang, Zhao Yao, Di Sun, Tao Jin, Guangyin Cao, Xin Cong, Gao Jensen, Christian S. Cheng, Xueqi |
| author_facet | Shao, Zezhi Wang, Fei Xu, Yongjun Wei, Wei Yu, Chengqing Zhang, Zhao Yao, Di Sun, Tao Jin, Guangyin Cao, Xin Cong, Gao Jensen, Christian S. Cheng, Xueqi |
| contents | Multivariate Time Series (MTS) analysis is crucial to understanding and managing complex systems, such as traffic and energy systems, and a variety of approaches to MTS forecasting have been proposed recently. However, we often observe inconsistent or seemingly contradictory performance findings across different studies. This hinders our understanding of the merits of different approaches and slows down progress. We address the need for means of assessing MTS forecasting proposals reliably and fairly, in turn enabling better exploitation of MTS as seen in different applications. Specifically, we first propose BasicTS+, a benchmark designed to enable fair, comprehensive, and reproducible comparison of MTS forecasting solutions. BasicTS+ establishes a unified training pipeline and reasonable settings, enabling an unbiased evaluation. Second, we identify the heterogeneity across different MTS as an important consideration and enable classification of MTS based on their temporal and spatial characteristics. Disregarding this heterogeneity is a prime reason for difficulties in selecting the most promising technical directions. Third, we apply BasicTS+ along with rich datasets to assess the capabilities of more than 45 MTS forecasting solutions. This provides readers with an overall picture of the cutting-edge research on MTS forecasting. The code can be accessed at https://github.com/GestaltCogTeam/BasicTS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_06119 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysis Shao, Zezhi Wang, Fei Xu, Yongjun Wei, Wei Yu, Chengqing Zhang, Zhao Yao, Di Sun, Tao Jin, Guangyin Cao, Xin Cong, Gao Jensen, Christian S. Cheng, Xueqi Machine Learning Artificial Intelligence Multivariate Time Series (MTS) analysis is crucial to understanding and managing complex systems, such as traffic and energy systems, and a variety of approaches to MTS forecasting have been proposed recently. However, we often observe inconsistent or seemingly contradictory performance findings across different studies. This hinders our understanding of the merits of different approaches and slows down progress. We address the need for means of assessing MTS forecasting proposals reliably and fairly, in turn enabling better exploitation of MTS as seen in different applications. Specifically, we first propose BasicTS+, a benchmark designed to enable fair, comprehensive, and reproducible comparison of MTS forecasting solutions. BasicTS+ establishes a unified training pipeline and reasonable settings, enabling an unbiased evaluation. Second, we identify the heterogeneity across different MTS as an important consideration and enable classification of MTS based on their temporal and spatial characteristics. Disregarding this heterogeneity is a prime reason for difficulties in selecting the most promising technical directions. Third, we apply BasicTS+ along with rich datasets to assess the capabilities of more than 45 MTS forecasting solutions. This provides readers with an overall picture of the cutting-edge research on MTS forecasting. The code can be accessed at https://github.com/GestaltCogTeam/BasicTS. |
| title | Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysis |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2310.06119 |