The answer is to enable autoscaling by setting min replicas to 2 and max replicas to 5. This is correct because a single n1-standard-4 node is being overwhelmed by concurrent requests, causing each prediction to queue and take 8-10 seconds; autoscaling distributes the inference load across multiple replicas, allowing parallel processing that directly reduces prediction latency for Vertex AI online predictions. On the Google Professional Data Engineer exam, this scenario tests your understanding that latency issues often stem from insufficient compute capacity rather than model size or input size, and that autoscaling is the primary mechanism for handling variable request volumes without sacrificing speed. A common trap is to assume a CPU-optimized machine or feature reduction will fix latency, but the bottleneck here is concurrency, not compute speed. Remember the memory tip: "Scale out, not up" — when latency spikes with a single node, add replicas before changing machine types.
PDE Operationalizing machine learning models Practice Question
This PDE practice question tests your understanding of operationalizing machine learning models. Read the scenario carefully and evaluate each option against the stated constraints before committing to an answer. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
Your company deploys a classification model on Vertex AI for online predictions. The model is an XGBoost model trained on tabular data with 500 features. The endpoint uses a single n1-standard-4 node. After deployment, users report that predictions take 8-10 seconds on average, while the required SLA is under 2 seconds. You have already verified that the model is not large (under 100 MB) and the input data size is small. The endpoint does not scale automatically. Which action should you take to reduce latency to meet the SLA? A) Change the machine type to n1-highcpu-4 to prioritize compute over memory. B) Enable autoscaling by setting min replicas to 2 and max replicas to 5. C) Switch to a custom container that preloads the model into memory. D) Reduce the number of features by half.
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Enable autoscaling by setting min replicas to 2 and max replicas to 5.
Option B is correct because the current single node is overloaded; autoscaling distributes traffic across multiple nodes, reducing latency for each request. Option A (CPU-optimized machine) may not help if the bottleneck is not CPU. Option C (preloading) is already default for Vertex AI. Option D (feature reduction) could degrade model accuracy and is not necessary.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
✗
Change the machine type to n1-highcpu-4 to prioritize compute over memory.
Why it's wrong here
High-CPU machines may not improve latency if the model is not CPU-bound; memory may still be sufficient.
✗
Reduce the number of features by half.
Why it's wrong here
Reducing features may harm model accuracy and is not a guaranteed solution; latency may still be high due to throughput.
✗
Switch to a custom container that preloads the model into memory.
Why it's wrong here
Vertex AI already preloads models into memory using the default container for XGBoost.
✓
Enable autoscaling by setting min replicas to 2 and max replicas to 5.
Why this is correct
Adding replicas offloads requests, reducing wait time and average latency.
Related concept
Read the scenario before looking for a memorised answer.
Common exam traps
Common exam trap: answer the scenario, not the keyword
Many certification questions include familiar terms but test a specific constraint. Read the exact wording before choosing an answer that is generally true but wrong for this case.
Detailed technical explanation
How to think about this question
This question should be treated as a scenario, not a definition check. Identify the problem, the constraint and the best action. Then compare each option against those facts.
KKey Concepts to Remember
Read the scenario before looking for a memorised answer.
Find the constraint that changes the correct option.
Eliminate answers that are true in general but not in this case.
Use explanations to understand the rule behind the answer.
TExam Day Tips
→Underline the problem statement mentally.
→Watch for words such as best, first, most likely and least administrative effort.
→Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
How this comes up in practice
An e-commerce site experiences heavy traffic on Black Friday and near-zero traffic during off-peak weeks. Rather than provisioning permanent large VMs, the team uses auto-scaling groups that add capacity automatically under load and reduce it overnight. Questions like this test whether you understand elasticity, availability zones, and cloud compute scaling patterns.
What to study next
Got this wrong? Here's your next step.
Identify which PDE exam domain this question belongs to, then review the specific concept being tested. Practise related questions in that domain and focus on understanding why each wrong answer is tempting — not just why the correct answer is right.
Operationalizing machine learning models — This question tests Operationalizing machine learning models — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Enable autoscaling by setting min replicas to 2 and max replicas to 5. — Option B is correct because the current single node is overloaded; autoscaling distributes traffic across multiple nodes, reducing latency for each request. Option A (CPU-optimized machine) may not help if the bottleneck is not CPU. Option C (preloading) is already default for Vertex AI. Option D (feature reduction) could degrade model accuracy and is not necessary.
What should I do if I get this PDE question wrong?
Identify which PDE exam domain this question belongs to, then review the specific concept being tested. Practise related questions in that domain and focus on understanding why each wrong answer is tempting — not just why the correct answer is right.
What is the key concept behind this question?
Read the scenario before looking for a memorised answer.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
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.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.