datamllab/tods

TODS: An Automated Time-series Outlier Detection System

47
/ 100
Emerging

Detecting unusual patterns or events in real-time data streams is crucial for many professionals. This system helps identify anomalies in time-series data, like sensor readings or financial transactions. You input your time-series data, and it outputs alerts or flags indicating suspicious points, patterns, or system-wide deviations. It's designed for data analysts, operations engineers, or fraud prevention specialists who need to quickly pinpoint abnormal behavior without deep machine learning expertise.

1,654 stars. No commits in the last 6 months.

Use this if you need an automated way to detect unusual or unexpected behavior in continuous streams of data, such as identifying a malfunctioning machine, a fraudulent transaction, or an abnormal network event.

Not ideal if your data is static, not time-based, or if you need to perform general classification or regression tasks rather than anomaly detection.

fraud-detection predictive-maintenance network-monitoring financial-trading system-health
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

1,654

Forks

205

Language

Python

License

Apache-2.0

Last pushed

Sep 11, 2023

Commits (30d)

0

Get this data via API

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

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