A comprehensive survey of deep learning for time series forecasting: architectural diversity and open challenges

Abstract Time series forecasting is a critical task that provides key information for decision-making across various fields, such as economic planning, supply chain management, and medical diagnosis. After the use of traditional statistical methodologies and machine learning in the past, various fundamental deep learning architectures such as MLPs, CNNs, RNNs, and GNNs have been developed and applied to solve time series forecasting problems. However, the structural limitations caused by the inductive biases of each deep learning architecture constrained their performance. Transformer models, which excel at handling long-term dependencies, have become significant architectural components for time series…

• NR
  National Research Foundation

  Award: BK21 FOUR
• SN
  Seoul National University

  Award: RS-2021-II211343
• NR
  National Research Foundation of Korea

  Awards: 2022R1A5A708390811, 2022R1A3B1077720
• MO
  Ministry of Science and ICT, South Korea

  Award: RS-2021-II211343
• S
  Samsung
• IF
  Institute for Information and Communications Technology Promotion

  Award: RS-2021-II211343