Question 704 of 1,000
Serving and Scaling ModelsmediumMultiple ChoiceObjective-mapped

PMLE Serving and Scaling Models Practice Question

This PMLE practice question tests your understanding of serving and scaling 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.

A company wants to run batch predictions on millions of records stored in BigQuery. They need to preprocess the data (e.g., feature engineering) before feeding it to the model. Which approach is most scalable and cost-effective?

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

Preprocess with Cloud Dataflow, output to Cloud Storage, then submit a Vertex AI batch prediction job.

Option D is the most scalable and cost-effective because Cloud Dataflow (Apache Beam) provides serverless, auto-scaling preprocessing that handles large volumes of data efficiently, and Vertex AI batch predictions natively read from Cloud Storage, avoiding the need to manage infrastructure. This decouples preprocessing from prediction, allowing each to scale independently and minimizing costs by using ephemeral, pay-per-use resources.

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.

  • Use a large DataProc cluster to preprocess and run batch predictions.

    Why it's wrong here

    DataProc is more complex and less cost-effective for preprocessing only; Vertex AI batch prediction can use Dataflow for preprocessing.

  • Preprocess inline in the batch prediction job using a custom container.

    Why it's wrong here

    Vertex AI batch prediction expects preprocessed input; preprocessing in the container is possible but less scalable than Dataflow.

  • Use a custom Python script on a Compute Engine instance.

    Why it's wrong here

    Not scalable for millions of records; single instance would be slow.

  • Preprocess with Cloud Dataflow, output to Cloud Storage, then submit a Vertex AI batch prediction job.

    Why this is correct

    Dataflow provides scalable preprocessing, and Vertex AI batch prediction reads from Cloud Storage.

    Related concept

    Read the scenario before looking for a memorised answer.

Common exam traps

Common exam trap: answer the scenario, not the keyword

A common mistake is assuming a single large cluster (Dataproc) or a single VM is sufficient for batch processing, when in fact serverless, auto-scaling services like Dataflow are more appropriate for large-scale, ephemeral preprocessing tasks.

Detailed technical explanation

How to think about this question

Cloud Dataflow uses the Apache Beam SDK to automatically parallelize preprocessing across many workers, dynamically scaling based on data volume using autoscaling algorithms that adjust the number of workers in real time. The output to Cloud Storage (e.g., Avro, TFRecord) is directly consumable by Vertex AI batch prediction, which reads from Cloud Storage using a distributed reader that leverages Google Cloud's internal high-throughput networking. In a real-world scenario, this pattern allows preprocessing of terabytes of data without provisioning any servers, and the batch prediction job can be submitted asynchronously, with results written back to Cloud Storage for downstream consumption.

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.

TExam Day Tips

  • 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

A startup's cloud architect reviews their monthly bill and notices costs are higher than expected for a long-running batch job. Switching from on-demand instances to Reserved Instances — or using Spot/Preemptible VMs — can reduce compute costs by up to 72 %. Questions like this test whether you understand the tradeoffs between commitment, flexibility, and cost across cloud pricing models.

Quick reference

Cloud Service Model Comparison

ModelYou ManageProvider ManagesExamples
IaaSOS, runtime, apps, dataHardware, hypervisor, networkingEC2, Azure VMs, GCP Compute Engine
PaaSApps and dataOS, runtime, middleware, hardwareElastic Beanstalk, Azure App Service
SaaSData and settings onlyEverything elseMicrosoft 365, Salesforce, Workday
FaaS / ServerlessFunction code onlyInfra, scaling, runtimeLambda, Azure Functions, Cloud Run
CaaSContainers and appsKubernetes, OS, hardwareEKS, AKS, GKE

What to study next

Got this wrong? Here's your next step.

Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.

Related practice questions

Related PMLE practice-question pages

Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.

Practice this exam

Start a free PMLE practice session

Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.

FAQ

Questions learners often ask

What does this PMLE question test?

Serving and Scaling Models — This question tests Serving and Scaling Models — Read the scenario before looking for a memorised answer..

What is the correct answer to this question?

The correct answer is: Preprocess with Cloud Dataflow, output to Cloud Storage, then submit a Vertex AI batch prediction job. — Option D is the most scalable and cost-effective because Cloud Dataflow (Apache Beam) provides serverless, auto-scaling preprocessing that handles large volumes of data efficiently, and Vertex AI batch predictions natively read from Cloud Storage, avoiding the need to manage infrastructure. This decouples preprocessing from prediction, allowing each to scale independently and minimizing costs by using ephemeral, pay-per-use resources.

What should I do if I get this PMLE question wrong?

Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.

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 →

How Courseiva writes practice questions · Editorial policy

Keep practising

More PMLE practice questions

Last reviewed: Jul 4, 2026

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.

Loading comments…

Sign in to join the discussion.

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.