- A
Implement a SageMaker Model Ensemble with two additional models to balance the load.
Why wrong: Incorrect. A model ensemble would increase the computational load on the endpoint, making the latency problem worse, not better.
- B
Replace the custom scaling policy with a target tracking scaling policy based on the number of invocations per instance, with a target value of 1000.
Correct. A target tracking scaling policy based on the number of invocations per instance allows the endpoint to scale out more quickly in response to traffic spikes, as the metric directly reflects demand.
- C
Implement a SageMaker Inference Pipeline with a pre-processing step to reduce model input size.
Why wrong: Incorrect. An inference pipeline adds a preprocessing step, which increases latency and could exacerbate the timeout issues.
- D
Switch to a GPU instance type, such as ml.p3.2xlarge, to increase compute capacity.
Why wrong: Incorrect. While a GPU instance provides more compute power, the fundamental issue is the scaling policy's reactivity. Without improving the scaling metric, the endpoint will still scale too slowly.
Using Target Tracking Scaling for Flash Sale Traffic Spikes
This MLA-C01 practice question tests your understanding of target tracking scaling policy. The scenario asks you to isolate a root cause — eliminate options that address a different problem before choosing. A key principle to apply: target tracking scaling policy. 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 financial services company uses Amazon SageMaker to deploy a fraud detection model for real-time inference. The model is deployed on an ml.m5.large instance with a SageMaker real-time endpoint. The endpoint has an auto scaling policy configured using a custom scaling policy based on average CPU utilization, with scale out threshold at 70% and scale in threshold at 30%. During a flash sale event, the traffic to the endpoint spikes tenfold within minutes. The endpoint fails to handle the load, resulting in increased latency and timeouts. The data science team needs to improve the scalability of the endpoint to handle sudden traffic spikes. Which solution should the team implement?
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
Replace the custom scaling policy with a target tracking scaling policy based on the number of invocations per instance, with a target value of 1000.
Option B is correct because a target tracking scaling policy based on invocations per instance provides a more direct and responsive metric for handling traffic spikes. CPU utilization can lag behind request surges, causing delayed scaling and increased latency. Option A is incorrect because adding a model ensemble increases computational load and does not solve scaling latency. Option C is incorrect because an inference pipeline adds preprocessing overhead, increasing latency. Option D is incorrect because switching to a GPU instance addresses compute capacity but not the scaling policy's responsiveness; the endpoint would still suffer from delayed scaling under the CPU-based policy.
Key principle: Target tracking scaling policy
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Implement a SageMaker Model Ensemble with two additional models to balance the load.
Why it's wrong here
Incorrect. A model ensemble would increase the computational load on the endpoint, making the latency problem worse, not better.
- ✓
Replace the custom scaling policy with a target tracking scaling policy based on the number of invocations per instance, with a target value of 1000.
Why this is correct
Correct. A target tracking scaling policy based on the number of invocations per instance allows the endpoint to scale out more quickly in response to traffic spikes, as the metric directly reflects demand.
Related concept
Target tracking scaling policy
- ✗
Implement a SageMaker Inference Pipeline with a pre-processing step to reduce model input size.
Why it's wrong here
Incorrect. An inference pipeline adds a preprocessing step, which increases latency and could exacerbate the timeout issues.
- ✗
Switch to a GPU instance type, such as ml.p3.2xlarge, to increase compute capacity.
Why it's wrong here
Incorrect. While a GPU instance provides more compute power, the fundamental issue is the scaling policy's reactivity. Without improving the scaling metric, the endpoint will still scale too slowly.
Common exam traps
Common exam trap: answer the scenario, not the keyword
A common trap is to think that upgrading to a more powerful instance (like GPU) solves scalability issues, but the core problem is the scaling policy's responsiveness, not raw compute capacity.
Detailed technical explanation
How to think about this question
Treat this as a scenario question. Identify the problem, the constraint, and the best action. Then compare each option against those facts.
KKey Concepts to Remember
- Target tracking scaling policy
- SageMaker real-time endpoint
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
Target tracking scaling policy
Real-world example
How this comes up in practice
An e-commerce site experiences heavy traffic on Black Friday and near-zero traffic during off-peak weeks. Rather than provisioning permanent large VMs, the team uses auto-scaling groups that add capacity automatically under load and reduce it overnight. Questions like this test whether you understand elasticity, availability zones, and cloud compute scaling patterns.
What to study next
Got this wrong? Here's your next step.
Review target tracking scaling policy, then practise related MLA-C01 questions on the same topic to reinforce the concept.
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.
ML Model Development practice questions
Practise MLA-C01 questions linked to ML Model Development.
Data Preparation for Machine Learning practice questions
Practise MLA-C01 questions linked to Data Preparation for Machine Learning.
Deployment and Orchestration of ML Workflows practice questions
Practise MLA-C01 questions linked to Deployment and Orchestration of ML Workflows.
ML Solution Monitoring, Maintenance, and Security practice questions
Practise MLA-C01 questions linked to ML Solution Monitoring, Maintenance, and Security.
ML Solution Monitoring, Maintenance and Security practice questions
Practise MLA-C01 questions linked to ML Solution Monitoring, Maintenance and Security.
MLA-C01 fundamentals practice questions
Practise MLA-C01 questions linked to MLA-C01 fundamentals.
MLA-C01 scenario practice questions
Practise MLA-C01 questions linked to MLA-C01 scenario.
MLA-C01 troubleshooting practice questions
Practise MLA-C01 questions linked to MLA-C01 troubleshooting.
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?
Target tracking scaling policy
What is the correct answer to this question?
The correct answer is: Replace the custom scaling policy with a target tracking scaling policy based on the number of invocations per instance, with a target value of 1000. — Option B is correct because a target tracking scaling policy based on invocations per instance provides a more direct and responsive metric for handling traffic spikes. CPU utilization can lag behind request surges, causing delayed scaling and increased latency. Option A is incorrect because adding a model ensemble increases computational load and does not solve scaling latency. Option C is incorrect because an inference pipeline adds preprocessing overhead, increasing latency. Option D is incorrect because switching to a GPU instance addresses compute capacity but not the scaling policy's responsiveness; the endpoint would still suffer from delayed scaling under the CPU-based policy.
What should I do if I get this MLA-C01 question wrong?
Review target tracking scaling policy, then practise related MLA-C01 questions on the same topic to reinforce the concept.
What is the key concept behind this question?
Target tracking scaling policy
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 →
Keep practising
More MLA-C01 practice questions
- A team is using SageMaker Pipelines to train a model. The pipeline has multiple steps: data processing, training, evalua…
- A machine learning team deploys a custom container image for an Amazon SageMaker training job. The container needs to ac…
- A machine learning engineer sees the above error in Amazon CloudWatch Logs for a SageMaker endpoint. What is the most li…
- A data scientist has trained a model that achieves 95% accuracy on the training set but only 70% on the test set. Which…
- Refer to the exhibit. A data scientist reviews the output of a SageMaker training job. The model has 95% training accura…
- A team is using Amazon SageMaker to train a neural network. They want to minimize training time while effectively explor…
Last reviewed: Jun 23, 2026
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.
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.
Sign in to join the discussion.