Preparing Practice Exam…
Please wait a moment while the system generates the exam questions, answers, and study session.
Please wait a moment while the system generates the exam questions, answers, and study session.
Google Cloud Certified Professional Machine Learning Engineer · Google Cloud
Select one answer.
Written by other learners. Comments can disagree with the marked answer — check the official documentation when in doubt.
Recall Formula: True Positives / (True Positives + False Negatives) If you only use messages flagged by the model as potentially inappropriate, you have True Positives and False Positives, but no False Negatives to measure Recall. This rules out A, B and D. => C is correct.
D is a common trap, I think and not suitable to measure model performance.
Option Why it fails Key issue A Measures volume, not correctness No quality metric B Only precision, biased No recall C Unbiased precision + recall Correct D Cannot compute recall Sampling bias