chenyuanTKCY/KDSelector
KDSelector proposes a novel knowledge-enhanced and data-efficient framework for learning a neural network-based model selector in the context of time series anomaly detection.
This project helps data scientists and machine learning engineers more efficiently build and deploy time series anomaly detection systems. It takes historical time series data and a set of candidate anomaly detection models as input, and outputs an optimized neural network-based model selector. This selector learns to pick the best anomaly detection model for new, unseen time series data.
Use this if you need to automate the selection of the best anomaly detection model for various time series datasets, especially if you have a large archive of historical data to learn from.
Not ideal if you are looking for a standalone anomaly detection algorithm rather than a system to select between multiple existing algorithms.
Stars
8
Forks
1
Language
Python
License
—
Category
Last pushed
Feb 25, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/chenyuanTKCY/KDSelector"
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.