Which metric is defined as the area under the ROC curve (AUC)?

Get ready for the GARP Risk and AI Exam with flashcards and multiple choice questions. Each question comes with hints and explanations. Prepare for success!

The area under the ROC curve is a metric that captures a model’s ability to discriminate between positive and negative cases across all possible decision thresholds. The ROC curve itself shows the true positive rate versus the false positive rate as you vary the threshold, and the AUC is the integral of that curve. A higher AUC indicates better discrimination, and it’s interpretable as the probability that a randomly chosen positive instance will receive a higher score than a randomly chosen negative one. This measure is threshold-independent, meaning it assesses ranking quality across all thresholds rather than relying on a single cutoff. Cleaning and tokenization are preprocessing steps, not evaluation metrics, while the F1 score is a single-threshold metric that blends precision and recall rather than capturing the overall ranking across thresholds.