Question 277 of 1,000

SageMaker Endpoint Auto Scaling — Optimize Costs with Target Tracking | AWS Certified Machine Learning Engineer Associate Explained

This MLA-C01 practice question tests your understanding of ml solution monitoring, maintenance, and security. Match the stated requirement to the specific cloud service, access model, or configuration option — many options are valid in isolation but not for this scenario. 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 uses a SageMaker endpoint for real-time inference. To reduce costs, they want to implement auto-scaling based on the number of invocations per instance. They also need to ensure that scaling actions are recorded for audit. Which TWO steps should they take? (Select TWO.)

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

Create a target tracking scaling policy based on the InvocationsPerInstance metric

Option A is correct because the InvocationsPerInstance metric is a predefined SageMaker metric that Application Auto Scaling can use with a target tracking scaling policy. This policy automatically adjusts the number of instances to maintain a target value for invocations per instance, directly reducing costs by scaling down when demand is low.

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.

  • Create a target tracking scaling policy based on the InvocationsPerInstance metric

    Why this is correct

    Target tracking with InvocationsPerInstance is a common approach to scale based on invocation load.

    Related concept

    Read the scenario before looking for a memorised answer.

  • Enable AWS CloudTrail to log auto-scaling API calls

    Why this is correct

    CloudTrail logs all API calls, including those made by Application Auto Scaling, providing an audit trail.

    Related concept

    Read the scenario before looking for a memorised answer.

  • Register the SageMaker endpoint as a scalable target with Application Auto Scaling

    Why this is correct

    Application Auto Scaling requires registration of the resource as a scalable target before applying a scaling policy.

    Related concept

    Read the scenario before looking for a memorised answer.

  • Enable SageMaker Model Monitor to track invocation counts

    Why it's wrong here

    Model Monitor tracks data quality, not invocation counts; CloudWatch already provides Invocations metric.

  • Publish custom metrics to CloudWatch for endpoint utilization

    Why it's wrong here

    While custom metrics could be used, the built-in InvocationsPerInstance metric is sufficient and simpler.

Common exam traps

Common exam trap: answer the scenario, not the keyword

The trap here is that candidates may think custom metrics are required for auto-scaling, but SageMaker automatically emits the InvocationsPerInstance metric, making custom publishing unnecessary, and they may confuse Model Monitor's role with scaling metrics.

Detailed technical explanation

How to think about this question

Application Auto Scaling uses the AWS Auto Scaling API to register a scalable target (the SageMaker endpoint variant) and then applies a scaling policy. The target tracking policy continuously monitors the InvocationsPerInstance metric (which is the average number of invocations per instance over a 1-minute period) and adjusts the desired instance count to keep the metric near the specified target value, using a proportional-integral-derivative (PID) control algorithm to avoid oscillations.

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.

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 MLA-C01 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 MLA-C01 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 MLA-C01 question test?

ML Solution Monitoring, Maintenance, and Security — This question tests ML Solution Monitoring, Maintenance, and Security — Read the scenario before looking for a memorised answer..

What is the correct answer to this question?

The correct answer is: Create a target tracking scaling policy based on the InvocationsPerInstance metric — Option A is correct because the InvocationsPerInstance metric is a predefined SageMaker metric that Application Auto Scaling can use with a target tracking scaling policy. This policy automatically adjusts the number of instances to maintain a target value for invocations per instance, directly reducing costs by scaling down when demand is low.

What should I do if I get this MLA-C01 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

Same concept, more angles

3 more ways this is tested on MLA-C01

These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.

Variation 1. A company uses SageMaker Inference Recommender to select the optimal endpoint configuration. After running the recommender, they receive a recommendation for a specific instance type and initial instance count. What should they do next to optimize costs over time?

medium
  • A.Use the recommended configuration without changes, as it is already optimal
  • B.Purchase a Savings Plan for the recommended instance type to reduce hourly cost
  • C.Set up auto-scaling with a target tracking policy based on the recommended metric
  • D.Manually adjust the instance count daily based on observed traffic

Why C: SageMaker Inference Recommender provides a baseline configuration. To optimize costs, they should apply auto-scaling with a target tracking policy based on the recommended metric, such as invocation count or latency.

Variation 2. A company uses SageMaker endpoints for real-time inference. They want to automatically scale the number of instances based on the number of outstanding requests. Which auto-scaling policy type should they choose?

medium
  • A.Scheduled scaling
  • B.Step scaling
  • C.Target tracking scaling
  • D.Simple scaling

Why C: Target tracking scaling adjusts the instance count to maintain a target metric value (e.g., average invocation count per instance). Step scaling uses predefined scaling adjustments based on alarm breaches but does not directly track a target. Simple scaling is not recommended for production. Scheduled scaling is for predictable patterns, not dynamic.

Variation 3. A machine learning engineer wants to reduce costs for a SageMaker real-time endpoint that experiences predictable traffic patterns with low traffic at night and high traffic during business hours. Which approach is most cost-effective while maintaining availability?

medium
  • A.Use a single large instance type that can handle peak traffic at all times
  • B.Configure an auto-scaling policy with target tracking based on the Invocations metric
  • C.Set up a scheduled scaling policy that manually adjusts instances at fixed times
  • D.Use SageMaker Inference Recommender to find the optimal instance type and then manually set instance count

Why B: Target tracking scaling policies automatically adjust instance count based on a metric like invocation count or CPU utilization. Step scaling can also be used but target tracking is simpler and more cost-effective for predictable patterns.

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 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.