decisionintelligence/TAB

[PVLDB 2025] TAB: Unified Benchmarking of Time Series Anomaly Detection Methods

37
/ 100
Emerging

This is a benchmarking library for evaluating time series anomaly detection models. It takes in various time series datasets and different anomaly detection algorithms, then outputs comprehensive performance comparisons based on various metrics and strategies. This tool is designed for researchers in time series anomaly detection who need to rigorously compare and validate different methods.

117 stars.

Use this if you are a researcher needing a standardized and reproducible way to evaluate and compare the performance of different time series anomaly detection models.

Not ideal if you are a practitioner looking for a ready-to-use anomaly detection solution for your specific business data.

time-series-analysis anomaly-detection model-benchmarking algorithm-evaluation research-validation
No License No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 7 / 25
Community 14 / 25

How are scores calculated?

Stars

117

Forks

13

Language

Jupyter Notebook

License

Last pushed

Nov 26, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/decisionintelligence/TAB"

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