I am working on an anomaly detection problem and have come across a paper(https://www.ijcai.org/proceedings/2019/0378.pdf), which shows results where in the ROC AUC value for a dataset is 0.566 and the PR AUC for the same dataset is 0.908. Can someone please explain to me in what case/scenarios this is possible?
$\begingroup$
$\endgroup$
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
1
Without reading the paper, the first scenario that comes to my mind is when you have imbalanced classes (very few instances of one class compared to the other). PR takes into account the provided class imbalance.
-
$\begingroup$ Your answer could be improved with additional supporting information. Please edit to add further details, such as citations or documentation, so that others can confirm that your answer is correct. You can find more information on how to write good answers in the help center. $\endgroup$– Community BotCommented Jan 13, 2023 at 0:33