microsoft/FLAML

support anomaly detection

Open

#413 aberto em 19 de jan. de 2022

Ver no GitHub
 (4 comments) (4 reactions) (0 assignees)Jupyter Notebook (560 forks)github user discovery
enhancementgood first issue

Métricas do repositório

Stars
 (4.364 stars)
Métricas de merge de PR
 (Métricas PR pendentes)

Description

Add a task type 'anomaly_detection', and at least one learner for it.

From my understanding there are multiple types of anomalies - point anomalies, contextual anomalies, and collective anomalies - and also different types of anomaly detection algorithms - nearest-neighbor, clustering, classification, and statistic based.

If anyone has any suggestions or requests for this task, please comment.

Guia do colaborador