decisionintelligence/CATCH
[ICLR 2025] CATCH: Channel-Aware Multivariate Time Series Anomaly Detection via Frequency Patching
This project helps operations engineers, data scientists, or system administrators analyze complex sensor readings or system metrics from multiple sources over time to identify unusual patterns. It takes in multivariate time series data, like logs from different server components or sensor readings from various parts of a machine, and outputs alerts or indicators of anomalous behavior, helping you pinpoint potential issues before they escalate.
162 stars.
Use this if you need to automatically detect subtle anomalies in interconnected time series data, such as identifying a performance degradation across multiple server metrics or a fault in industrial equipment based on a mix of sensor signals.
Not ideal if your data is not time-series based, you only have single-channel data, or you need a lightweight, real-time solution for very high-frequency data streams.
Stars
162
Forks
17
Language
Python
License
—
Category
Last pushed
Dec 30, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/decisionintelligence/CATCH"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yzhao062/pyod
A Python Library for Outlier and Anomaly Detection, Integrating Classical and Deep Learning Techniques
unit8co/darts
A python library for user-friendly forecasting and anomaly detection on time series.
elki-project/elki
ELKI Data Mining Toolkit
raphaelvallat/antropy
AntroPy: entropy and complexity of (EEG) time-series in Python
Minqi824/ADBench
Official Implement of "ADBench: Anomaly Detection Benchmark", NeurIPS 2022.