easyMultiple Choice
MLA-C01 Practice Question: A company has deployed a SageMaker real-time…
A company has deployed a SageMaker real-time endpoint for a model that predicts customer churn. The endpoint uses a single ml.m5.large instance. After deployment, the team notices that during peak hours, the endpoint returns 5xx errors for about 20% of requests. The endpoint has not been configured with any scaling policy. The team needs to resolve this issue with minimal cost increase. Which solution should the team implement?
⚠ Common exam trap
It's easy for candidates to confuse 'scaling up' (increasing instance size) with 'scaling out' (adding more instances), and overlook that Auto Scaling with a target tracking policy is the most cost-effective way to handle variable traffic, as it matches capacity to demand in real time.
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
✓
Enable Auto Scaling for the endpoint with a target tracking policy based on the average InvocationsPerInstance metric.
Enabling Auto Scaling with a target tracking policy based on the average InvocationsPerInstance metric dynamically adjusts the number of instances in response to traffic spikes, preventing 5xx errors during peak hours without over-provisioning. This approach minimizes cost by scaling only when needed, unlike manual instance upgrades or batch transforms that either increase baseline cost or introduce 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.
- ✗
Deploy the model to a multi-model endpoint to reduce resource utilization.
Why it's wrong here
Multi-model endpoints host several models behind one container to cut hosting costs, but a single model still receives the same instance capacity, so peak concurrency 5xx errors persist. It tempts when consolidating many low-traffic models, not when one model needs additional instances.
- ✓
Enable Auto Scaling for the endpoint with a target tracking policy based on the average InvocationsPerInstance metric.
Why this is correct
Target tracking on InvocationsPerInstance scales instance count to match request volume, so peak-hour demand no longer overwhelms the single ml.m5.large instance and 5xx errors subside. Because scaling adds capacity only when invoked, cost stays proportional to load, satisfying the minimal-cost-increase constraint.
- ✗
Increase the instance type to ml.m5.xlarge to handle more concurrent requests.
Why it's wrong here
A larger instance raises per-instance capacity but provides no horizontal scaling, so peak-hour concurrency still exceeds limits and 5xx errors continue. It tempts as a quick vertical fix, yet an automatic scaling policy adds instances only under load, costing less overall.
- ✗
Use SageMaker batch transform instead of real-time inference to process peak traffic asynchronously.
Why it's wrong here
Batch transform processes stored data offline, so it cannot serve the synchronous per-request churn predictions the endpoint provides. It tempts for large asynchronous scoring jobs, but the 5xx errors stem from concurrency limits on real-time traffic, which batch transform does not address.
Visual reference
Go deeper
Related to this question
About these practice questions
One of 665 original MLA-C01 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 MLA-C01 practice question is part of Courseiva's free Amazon Web Services 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 MLA-C01 exam.