microsoft/FLAML

support anomaly detection

Open

#413 geöffnet am 19. Jan. 2022

Auf GitHub ansehen
 (4 Kommentare) (4 Reaktionen) (0 zugewiesene Personen)Jupyter Notebook (560 Forks)github user discovery
enhancementgood first issue

Repository-Metriken

Stars
 (4.364 Stars)
PR-Merge-Metriken
 (PR-Metriken ausstehend)

Beschreibung

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.

Contributor Guide