mediumMultiple Choice
PMLE Practice Question: A financial services company wants to detect…
A financial services company wants to detect fraudulent transactions in real-time. They have a trained XGBoost model that runs on a single Compute Engine instance. The current solution processes about 100 transactions per second, but they need to scale to 10,000 transactions per second. Which approach should they take?
⚠ Common exam trap
Google Cloud often tests the misconception that vertical scaling (bigger VM) is sufficient for large throughput increases, when in reality horizontal scaling with a managed service like Vertex AI is required for elasticity and high availability.
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
✓
Deploy the model to Vertex AI Prediction with autoscaling enabled
Vertex AI Prediction with autoscaling is the correct choice because it is purpose-built for serving ML models at scale, automatically adjusting the number of compute nodes based on incoming request traffic. This allows the company to seamlessly handle the increase from 100 to 10,000 transactions per second without manual intervention, while XGBoost is natively supported as a framework.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Increase the VM to a machine type with more vCPUs and memory
Why it's wrong here
Vertical scaling remains capped by a single machine's CPU and memory ceiling, so it cannot reliably reach 10,000 transactions per second and offers no horizontal redundancy. It is tempting as the smallest change to existing infrastructure, but it does not distribute inference across replicas.
- ✓
Deploy the model to Vertex AI Prediction with autoscaling enabled
Why this is correct
Vertex AI Prediction autoscaling distributes inference across managed replicas, so throughput scales horizontally beyond a single Compute Engine instance's ceiling. This satisfies the 10,000 transactions per second requirement while preserving the trained XGBoost model, which Vertex AI serves natively as a pre-built container.
- ✗
Use Dataflow to process transactions in micro-batches every second
Why it's wrong here
Micro-batching every second adds latency and Dataflow is built for batch and streaming data pipelines, not for serving a trained XGBoost model at low latency. It is tempting as a managed autoscaling ingestion path, but it does not host the model itself.
- ✗
Rewrite the model as a Cloud Function triggered by Pub/Sub messages
Why it's wrong here
Cloud Functions impose execution timeouts and cold-start latency, and rewriting XGBoost into that runtime is impractical for sustained 10,000 transactions per second. It is tempting as a serverless event-driven trigger, but it targets lightweight stateless handlers, not high-throughput model serving.
Go deeper
Related to this question
About these practice questions
One of 775 original PMLE 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 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.