Use raw auc then normalize for detection test #236
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
To my opinion, the 2 * ( 1-max(0.5,auc) ) transformation is a normalization procedure which transforms the 0.5-to-1-lower-is-better auc metric into a 0-to-1-higher-is-better metric.
I propose to move it to the normalization method and keep the raw auc score clipped to [0.5,1] as a raw detection measure.
One reason is that auc is a well known and understood metric.