For a rare-fraud detection task, which metric pair is usually more informative than accuracy alone?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — Precision and recall (or PR-AUC), because accuracy can look high while missing almost all fraud cases
Full explanation below image
Full Explanation
The correct answer is: Precision and recall (or PR-AUC), because accuracy can look high while missing almost all fraud cases. This matches standard ML/AI engineering practice for Domain 2: Evaluation. Distractors confuse adjacent concepts or unsafe operational shortcuts. In production, validate with held-out data, monitoring, and governance appropriate to risk.