Welcome to the UEA & UCR Time Series Classification Repository

NEW: the univariate TSC archive has been relaunched with 128 datasets. Download all the data with the link below. For info on each follow the datset tab. The new UCR TSC archive can be referenced with this paper.

NEW: the multivariate TSC archive has been launched with 30 datasets. Download all the data with the link below. For info on each follow the datset tab. The new UEA MTSC archive can be referenced with this paper.

This website is an ongoing project to develop a comprehensive repository for research into time series classification. If you use the results or code, please cite the paper "Anthony Bagnall, Jason Lines, Aaron Bostrom, James Large and Eamonn Keogh, The Great Time Series Classification Bake Off: a Review and Experimental Evaluation of Recent Algorithmic Advances, Data Mining and Knowledge Discovery, 31(3), 2017". Paper Link, Bibtex Link.

If you want to just reference the website, please do so as: "Anthony Bagnall, Jason Lines, William Vickers and Eamonn Keogh, The UEA & UCR Time Series Classification Repository, www.timeseriesclassification.com".

This website is supported by the UK Engineering and Physical Sciences grant number EP/ M015087/1.

Download all of the new 128 UCR Time Series Classification datasets

The data are in text files and Weka formatted ARFF format and about 500 MB.

Download all of the new 30 multivariate UEA Time Series Classification datasets

The data are in text files and Weka formatted ARFF format and about 2GB.

Recommend Papers and Donate Datasets

Submit a Dataset  

We are constantly looking to expand the TSC repository and include as many datasets as we can. If you think you have suitable dataset please submit it here for review and we'll do our best to include it into the repository. If it is included we will reference you under the dataset source!

Recommend a Paper  

If you have written a paper or know of a paper that you believe should be include in the repository please tell us! Click the button below to submit a review request. All included publications will be fully cited and added to the bibliography (also included in the bibtex file).