Database Reference
In-Depth Information
The ROC curve
The area under the ROC curve (commonly referred to as AUC) represents an average
value. Again, an AUC of 1.0 will represent a perfect classifier. An area of 0.5 is referred
to as the random score. Thus, a model that achieves an AUC of 0.5 is no better than ran-
domly guessing.
Note
As both the area under the PR curve and the area under the ROC curve are effectively nor-
malized (with a minimum of 0 and maximum of 1), we can use these measures to compare
models with differing parameter settings and even compare completely different models.
Thus, these metrics are popular for model evaluation and selection purposes.
