1
$\begingroup$

how do I evaluate K-means clustering anomaly detection method as there is no labelled data of anomaly class. To find the cluster (K), I have used the silhouette score from Scikit learn library. Scikit learn K-means were used too.

Improve this question
$\endgroup$
2
  • $\begingroup$ Is the goal to compare models or hyperparameters? What kind of evaluation are you looking to do? $\endgroup$
    – Jon Nordby
    Commented Mar 27, 2020 at 19:10
  • $\begingroup$ im trying to apply in into physical staff access pattern. $\endgroup$
    – Nite
    Commented Mar 28, 2020 at 19:32

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.