I found this Scikit Learn page explaining how to use different algorithms to detect outliers:
https://scikit-learn.org/stable/modules/outlier_detection.html
Is it possible to set a group of instances as non-outliers so that the algorithms understand that those specific points should not be detected as outliers?
Advertisement
Answer
If you have enough so called non-outliers for training, one option is to use Novelty detection with Local Outlier Factor . You will train using all your non-outliers, then try to detect outliers with the rest of the data