AnomalyDetection is an R package developed by Twitter for detecting anomalies in seasonal univariate time series. It implements the Seasonal Hybrid Extreme Studentized Deviate (S‑H‑ESD) test, which reliably identifies both global and local outliers in data with trends and seasonality—commonly applied to system metrics, engagement data, and business KPIs.

Features

  • Detects anomalies robustly even under seasonality and trend
  • Implements S‑H‑ESD: hybrid ESd with seasonal decomposition
  • R package easy to integrate into analytics workflows
  • Scalable for large series or batch processing
  • Produces clear diagnostic output and flags
  • Used extensively for system and product telemetry analysis

Project Samples

AnomalyDetection Screenshot 1

Project Activity

See All Activity >

Categories

System

License

GNU General Public License version 3.0 (GPLv3)

Follow AnomalyDetection

AnomalyDetection Web Site

Other Useful Business Software
Auth for GenAI | Auth0 Icon
Auth for GenAI | Auth0

Enable AI agents to securely access tools, workflows, and data with fine-grained control and just a few lines of code.

Easily implement secure login experiences for AI Agents - from interactive chatbots to background workers with Auth0. Auth for GenAI is now available in Developer Preview
Try free now
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of AnomalyDetection!

Additional Project Details

Operating Systems

Linux, Mac, Windows

Programming Language

R

Related Categories

R System Software

Registered

3 days ago
Report inappropriate content