Area Under the Curve
What is the AUC?
Answer
Three things to know/remember here:
Simply said, the AUC is a single numerical metric used to evaluate and compare classification models. It calculates the area under the ROC curve.
The AUC can be interpreted as the probability that a randomly chosen positive observation (from the testing dataset) is ranked higher (this refers to the prediction) than a randomly chosen negative instance.
In general, an AUC of 1.0 indicates a perfect classifier, an AUC of 0.5 represents random guessing, and an AUC below 0.5 implies worse-than-random performance, meaning predictions could be inverted to improve accuracy.