Courseiva
mediumMultiple ChoiceObjective-mapped

MLA-C01 Practice Question: A company's SageMaker endpoint is experiencing…

A company's SageMaker endpoint is experiencing increased latency during peak hours. The endpoint uses a single ml.m5.large instance. The deployment is critical and must maintain low latency. Which action is MOST effective to reduce latency without sacrificing cost efficiency?

⚠ Common exam trap

A common mix-up: candidates confuse Elastic Inference (Option B) as a cost-effective latency fix, but it does not address the capacity bottleneck from a single instance; the exam tests whether you recognize that scaling out is the correct approach for handling variable traffic loads.

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

Add an auto-scaling policy based on request count

Adding an auto-scaling policy based on request count directly addresses the root cause of increased latency during peak hours: insufficient compute capacity. Auto-scaling dynamically adds more ml.m5.large instances when request count rises, distributing the load and reducing latency, while scaling down during off-peak hours to maintain cost efficiency. This is the most effective solution for a critical deployment that must maintain low latency without sacrificing cost.

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 multiple variants with A/B testing

    Why it's wrong here

    A/B testing routes traffic between variants, but does not directly address latency.

  • Use Elastic Inference to attach an accelerator

    Why it's wrong here

    Elastic Inference reduces cost per inference but may not resolve latency if the instance is already saturated.

  • Switch to a ml.c5.large instance

    Why it's wrong here

    Changing instance family may not address the root cause of insufficient capacity during peaks.

  • Add an auto-scaling policy based on request count

    Why this is correct

    Auto-scaling adjusts instance count to match demand, reducing latency during spikes while minimizing cost.

  • Enable SageMaker Model Monitor

    Why it's wrong here

    Model Monitor is for drift detection, not for improving latency.

About these practice questions

Courseiva writes every MLA-C01 question from scratch — 835 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →

How Courseiva writes practice questions · Editorial policy

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.