This repository curates a comprehensive collection of recent research papers and associated code/resources in time series analysis. It targets researchers and practitioners in machine learning and data science, providing a valuable, up-to-date reference for advancements in forecasting, anomaly detection, and related fields.

How It Works

The repository is structured by sub-topic within time series analysis, such as forecasting, anomaly detection, and representation learning. Each entry typically includes the paper's title, a link to its code (if available), and its source conference or journal. Special markers highlight highly cited papers (💛) and personal recommendations (⭐).

Quick Start & Requirements

This is a curated list of papers and does not require installation or execution. Links to external resources like GitHub repositories or official documentation are provided within the paper entries.

Highlighted Details

• Covers a broad spectrum of time series tasks including forecasting, anomaly detection, early classification, irregular time series learning, representation learning, and causal discovery.
• Regularly updated with papers from major conferences (NeurIPS, ICML, ICLR, KDD, AAAI, WWW, VLDB) and journals, with recent additions from 2025 conferences.
• Includes direct links to code repositories for many papers, facilitating practical implementation and experimentation.
• Features curated sections for "Theory Resource" and "Code Resource" offering broader learning materials and toolkits.

Maintenance & Community

The repository is actively maintained, with recent updates reflecting new papers from early 2025. Contributions and suggestions are welcomed via issues or pull requests.

Licensing & Compatibility

The repository itself is likely under a permissive license (e.g., MIT, Apache 2.0, as is common for "awesome" lists), but the licensing of the linked papers and their associated code must be checked individually. Compatibility for commercial use depends entirely on the licenses of the linked external projects.

Limitations & Caveats

This is a curated list and not a software library; it does not provide direct functionality. The availability and quality of linked code vary, and some papers may not have publicly available code. The "personal reference" markers (⭐) represent subjective recommendations.