Deep Time Series Models: A Comprehensive Survey and Benchmark

TL;DR

This paper reviews deep time series models, introduces a comprehensive benchmark library TSLib with 41 models across 30 datasets and 5 tasks, and provides empirical insights into model-task suitability.

Contribution

It offers a detailed survey of deep time series modeling, develops TSLib benchmark with extensive models and datasets, and evaluates models to guide future research and application.

Findings

Models with specific structures excel at particular tasks.

Evaluation reveals strengths and limitations of 16 popular models.

Benchmark facilitates fair comparison and future research.

Abstract

Time series, characterized by a sequence of data points organized in a discrete-time order, are ubiquitous in real-world scenarios. Unlike other data modalities, time series present unique challenges in learning and modeling due to their intricate and dynamic nature, including the entanglement of nonlinear patterns and time-variant trends. Recent years have witnessed remarkable breakthroughs in time series analysis, with techniques shifting from traditional statistical methods to contemporary deep learning models. In this paper, we delve into the design of deep time series models across various analysis tasks and review the existing literature from two perspectives: basic modules and model architectures. Further, we develop and release Time Series Library (TSLib) as a fair benchmark of deep time series models for diverse analysis tasks. TSLib implements 41 prominent models, including both small- and large-scale time series models, covers 30 datasets from different domains, and supports 5 prevalent analysis tasks. Based on TSLib, we evaluate 16 popular deep time series models and 6 advanced time series foundation models. Empirical findings indicate that models with specific structures are apt only at distinct analytical tasks, providing insights for research and adoption of deep time series models. Code and datasets are available at https://github.com/thuml/Time-Series-Library.