AWS Certified AI Practitioner (AIF-C01) — Question 171

A financial company is developing a fraud detection system that flags potential fraud cases in credit card transactions. Employees will evaluate the flagged fraud cases. The company wants to minimize the amount of time the employees spend reviewing flagged fraud cases that are not actually fraudulent.

Which evaluation metric meets these requirements?

Answer options

• A. Recall
• B. Accuracy
• C. Precision
• D. Lift chart

Correct answer: C

Explanation

Precision is the correct evaluation metric because it measures the proportion of true positive cases among all flagged cases, helping to minimize the time spent on reviewing false positives. Recall focuses on identifying true positives but does not account for false positives, while accuracy does not specifically address the issue of false flags. A lift chart is more of a visual tool for assessing the performance of a model rather than a specific metric for evaluation.