ermshaua/time-series-segmentation-benchmark

This repository contains the time series segmentation benchmark (TSSB).

44
/ 100
Emerging

This project provides a standardized set of annotated time series data for evaluating segmentation algorithms. It takes various time series datasets, merges them to create data with distinct patterns and known 'change points,' and outputs these segmented time series ready for algorithm testing. Researchers and practitioners working on algorithms that detect changes in sequential data would use this to benchmark their methods.

No commits in the last 6 months.

Use this if you are developing or evaluating algorithms that automatically identify changes or distinct phases within time series data and need a reliable, pre-segmented dataset for testing.

Not ideal if you need to perform time series segmentation on your own raw data or are looking for a segmentation algorithm to apply to a specific business problem.

time-series-analysis change-point-detection algorithm-evaluation data-pattern-recognition scientific-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

82

Forks

19

Language

Jupyter Notebook

License

BSD-3-Clause

Last pushed

Mar 31, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ermshaua/time-series-segmentation-benchmark"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.