hardMultiple Choice
PDE Practice Question: You manage a large-scale machine learning system…
You manage a large-scale machine learning system that recommends products to users. The model is a deep neural network trained on TensorFlow and deployed on Vertex AI Endpoint with global load balancing. The model receives over 10,000 requests per second. Recently, the team added a new feature: the user's current geographic location (latitude/longitude). After deploying the updated model, you notice that the average prediction latency has doubled, and the error rate has increased, particularly for requests from regions far from the model's primary training data (North America). You suspect the location feature is causing issues. What should you do to diagnose and mitigate the problem?
⚠ Common exam trap
PDE often tests whether candidates jump to infrastructure scaling (adding replicas) or feature removal instead of first using observability tooling to isolate the root cause before mitigating.
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
✓
Examine the latency breakdown using Cloud Monitoring to see if the location feature is causing computationally expensive operations, then consider feature engineering like bucketing coordinates.
The correct first step is to gather diagnostic data before making changes. Cloud Monitoring provides latency breakdowns per operation, letting you confirm whether the new location feature (e.g., raw latitude/longitude floats feeding into dense layers or distance computations) is the bottleneck. Once confirmed, feature engineering such as geohash bucketing or embedding coordinates reduces computational cost and improves generalization for out-of-region requests.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Remove the location feature from the model and retrain without it to restore performance.
Why it's wrong here
Discarding the feature removes the diagnostic signal without establishing why it degraded performance, and the errors concentrate in regions far from North American training data. Removal is tempting because it restores the previous model, the right action when a feature is confirmed harmful and cannot be made to generalise.
- ✗
Increase the number of replicas for the endpoint to handle the increased latency.
Why it's wrong here
Adding replicas addresses throughput capacity, not the doubled latency and region-specific errors caused by the new latitude/longitude feature's distribution shift. Scaling is tempting because it is the standard remedy when latency rises from genuine traffic growth, which is when extra Vertex AI Endpoint replicas would be the correct response.
- ✗
Switch to a regional endpoint in North America to reduce latency for the majority of users.
Why it's wrong here
A North American regional endpoint cannot fix errors from distant regions and abandons the global load balancing the design requires. Regional endpoints are tempting because they genuinely cut latency when traffic is concentrated in one geography and data residency rules demand in-region processing.
- ✓
Examine the latency breakdown using Cloud Monitoring to see if the location feature is causing computationally expensive operations, then consider feature engineering like bucketing coordinates.
Why this is correct
Cloud Monitoring's latency breakdown isolates whether the latitude/longitude feature introduces expensive preprocessing or distance computations, satisfying the need to pinpoint the doubling's source. Bucketing coordinates into discrete geographic regions then reduces cardinality and sparsity, addressing the elevated error rates for requests far from North American training data.
Go deeper
Related to this question
About these practice questions
One of 747 original PDE practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Google Cloud exam blueprint
This PDE 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 PDE exam.