A Comprehensive Survey of Deep Learning for Multivariate Time Series Forecasting: A Channel Strategy Perspective

TL;DR

This survey provides a structured, three-level taxonomy of channel strategies for deep learning-based multivariate time series forecasting, organizing methods by strategy (CI/CD/CP), mechanism (Transformer/MLP/CNN/GNN), and channel characteristics. It analyzes trade-offs across efficiency, robustness, generalizability, and capacity, and highlights concrete future directions, including horizon-aware correlations, multi-component and multi-frequency characteristics, multimodal integration, and foundation-model approaches. By cataloging representative methods and their mechanisms, the work offers a practical roadmap for researchers to design and evaluate cross-channel modeling in MTSF. The accompanying GitHub resource curates the papers discussed, facilitating reproducibility and further exploration.

Abstract

Multivariate Time Series Forecasting (MTSF) plays a crucial role across diverse fields, ranging from economic, energy, to traffic. In recent years, deep learning has demonstrated outstanding performance in MTSF tasks. In MTSF, modeling the correlations among different channels is critical, as leveraging information from other related channels can significantly improve the prediction accuracy of a specific channel. This study systematically reviews the channel modeling strategies for time series and proposes a taxonomy organized into three hierarchical levels: the strategy perspective, the mechanism perspective, and the characteristic perspective. On this basis, we provide a structured analysis of these methods and conduct an in-depth examination of the advantages and limitations of different channel strategies. Finally, we summarize and discuss some future research directions to provide useful research guidance. Moreover, we maintain an up-to-date Github repository (https://github.com/decisionintelligence/CS4TS) which includes all the papers discussed in the survey.

Figures (5)

• Figure 1: Channel strategy overview.
• Figure 2: Transformer-based mechanism for channel strategy.
• Figure 3: MLP, CNN-based mechanism for channel strategy.
• Figure 4: GNN-based mechanism for channel strategy.
• Figure 5: Characteristics perspective overview.