Failure detection rate (FDR) and false alarm rate (FAR) are used in anomaly detection and failure detection domains to evaluate the classification model performance. However, I don't see any clear definition of failure detection rate (FDR) and false alarm rate (FAR) so that we can relate these with precision and recall. Can we relate failure detection rate (FDR) and false alarm rate (FAR) to precision and recall ?
3
-
$\begingroup$ All these measures are calculated from the various quantities of True Positives, False Negatives, False Positives and True Negatives that you see in a Confusion Matrix, so all can be related to each other. If you have these four numbers you can calculate all of these metrics. Check out the "Table of Confusion" on wikipedia - en.wikipedia.org/wiki/Confusion_matrix $\endgroup$– rw2Commented May 21, 2021 at 9:32
-
$\begingroup$ @rw2 Is failure detection rate (FDR) same as true positive rate? $\endgroup$– QuantamCommented May 23, 2021 at 1:13
-
$\begingroup$ Yes, I believe so - both are TP/(TP+FN) $\endgroup$– rw2Commented May 24, 2021 at 8:12
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
As I mentioned in the comments, all of these metrics are calculated from measures in a typical confusion matrix of True Positives, False Positives, True Negatives and False Negatives - see en.wikipedia.org/wiki/Confusion_matrix
Recall is the same as True Positive Rate, which is also sometimes called Failure Detection Rate - TP/(TP+FN)
False Alarm Rate is the same as the False Positive Rate - FP/(FP+TN).
