# twitter/AnomalyDetection

Anomaly Detection with R

Repository: https://github.com/twitter/AnomalyDetection
Canonical: https://ross.abutalabs.com/products/anomalydetection
Language: R
License: GPL-3.0
License Family: copyleft
Archived: true
Last push: 2019-08-30T19:49:16+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 4285, "days_push": 2560, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3606, forks 764 (observed 2026-08-28T04:08:11.530457+00:00)

## What it is
An R package from Twitter that detects anomalies in time series and numeric vectors using the Seasonal Hybrid ESD (S-H-ESD) algorithm, robust to seasonality and trend. It includes visualization support for exploring detected anomalies.

## Use cases
- detect anomalies in system metrics after a software release
- find outliers in user engagement data after an A/B test
- detect anomalies in time series with seasonality and trend
- spot outliers in a vector of numeric values without timestamps
- analyze anomalies in financial or econometric data
- visualize anomalies in long time series like minutely data

## When to choose
- you work in R and need statistically robust anomaly detection on seasonal time series
- you need to detect both global and local anomalies in metrics data
- you want built-in visualization of detected anomalies

## When to avoid
- you need a maintained library with recent updates and active support
- you need real-time streaming anomaly detection
- you work outside R and don't want an R runtime dependency

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, data-science, data-visualization
- domain: data-science, analytics, time-series
- platform: python, cross-platform
- tags: r-package, anomaly-detection, time-series, s-h-esd, statistics

## Member repositories
- twitter/AnomalyDetection (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:11.530457+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:33:42.275796+00:00, confidence not recorded.
  - readme: https://github.com/twitter/AnomalyDetection (fetched 2026-08-28T04:08:11.530457+00:00, sha b012865f1530)
- Data as of 2026-08-30T08:39:29.467469+00:00.