Lleyton-Ariton/oddity

Time series anomaly detection via decomposition and gaussian process regression.

33
/ 100
Emerging

This tool helps you automatically spot unusual patterns or "oddities" in your time-based data, like sensor readings or sales figures. You input your historical time series data, and it identifies and highlights points that deviate significantly from the expected trend and seasonal cycles. Operations managers, data analysts, and anyone monitoring metrics over time can use this to quickly pinpoint anomalies that might indicate problems or opportunities.

No commits in the last 6 months.

Use this if you need to detect subtle or obvious anomalies in datasets that show clear trends and repeating seasonal patterns, whether daily, weekly, or yearly.

Not ideal if you need real-time, continuous anomaly detection on a live data stream, as it's currently designed for analyzing fixed, historical datasets.

operations-monitoring data-analysis predictive-maintenance fraud-detection performance-monitoring
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

21

Forks

3

Language

Rust

License

GPL-3.0

Last pushed

May 22, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Lleyton-Ariton/oddity"

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