Question 37
UnclassifiedWhat does ROC-AUC measure in a binary classification model?
Correct answer: B
Explanation
ROC-AUC measures how well a binary classifier separates classes by ranking positives above negatives across thresholds. ROC is the "receiver operating characteristic" curve, and AUC is the area under that curve, so a higher value means better discrimination between positive and negative samples.
Why each option is right or wrong
A. Accuracy at a single decision threshold
B. The model's ability to rank positive samples higher than negative samples across all thresholds
ROC-AUC is defined as the area under the Receiver Operating Characteristic curve, which plots true positive rate against false positive rate as the decision threshold varies from 0 to 1. In binary classification, that area summarizes the probability that a randomly chosen positive instance receives a higher score than a randomly chosen negative instance, so it directly tests ranking performance rather than any single cutoff.
C. Mean squared error between predicted and true values
D. How well the predicted probabilities are calibrated to observed outcomes