mediumMultiple Choice
PMLE Practice Question: Refer to the exhibit
Exhibit
resource.type="ml_job" jsonPayload.@type="type.googleapis.com/google.cloud.ml.v1.PredictionError" severity=ERROR
Refer to the exhibit. What is the purpose of this query?
⚠ Common exam trap
Google Cloud often tests the distinction between log-based monitoring (for errors) and metric-based monitoring (for counts, latency, drift), so candidates mistakenly choose 'count all prediction requests' when the query clearly filters for failures, not all requests.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
To find prediction errors in Cloud Logging
The query filters Cloud Logging entries for the string 'prediction failed', which directly indicates prediction errors logged by the ML prediction service. This is a common pattern for monitoring model inference failures in production, not for measuring drift, counting requests, or measuring latency.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
To detect data drift
Why it's wrong here
The query measures inference timing, not input-versus-training distribution differences, so it cannot detect data drift. Drift detection requires comparing feature or prediction distributions over time against a baseline. Latency monitoring is intended for performance tracking, which is what this query actually does.
- ✓
To find prediction errors in Cloud Logging
Why this is correct
Cloud Logging filters entries by severity and payload fields, surfacing mismatches between predicted and actual values logged by the model. This satisfies the stem's requirement to identify prediction errors, since the query targets error-level log entries rather than training metrics or infrastructure events.
- ✗
To count all prediction requests
Why it's wrong here
The query computes a latency statistic, not a tally of prediction requests, so it cannot count them. Counting requests requires an aggregate over request events or a row count of logged predictions. Latency measurement is intended for performance monitoring, which is what this query actually performs.
- ✗
To monitor model latency
Why it's wrong here
The query aggregates prediction counts rather than measuring inference duration, so it cannot report model latency. Latency monitoring requires timing metrics such as request duration or percentile distributions. Counting requests is intended for traffic volume or usage tracking, which is what this query actually returns.
Go deeper
Related to this question
About these practice questions
This PMLE question is part of Courseiva's 775-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This PMLE practice question is part of Courseiva's free Google Cloud certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the PMLE exam.