QuestionQ75

VerifiedArchitecting low-code AI solutions

You work for a credit card company and have been asked to build a custom fraud-detection model from historical data by using AutoML Tables. You must prioritize detecting fraudulent transactions while minimizing false positives. Which optimization objective should be used to train the model?

Explanation

Precision measures the proportion of transactions predicted as fraudulent that are actually fraudulent, so maximizing precision minimizes false positives. The Precision at Recall objective maximizes that precision while maintaining the selected recall level for detecting fraud. Google Cloud documents this objective as optimizing precision at a specific recall value.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!