MLS-C01 Feature selection for latency Practice Question
A company uses SageMaker to deploy a real-time inference endpoint for a fraud detection model. The model is an XGBoost model trained on 50 features. The endpoint receives 100 requests per second, but latency is higher than the required 200 ms. The team wants to reduce latency without retraining. What should they do?
⚠ Common exam trap
The trap is that candidates may assume Elastic Inference works for any model type, but it is specifically for deep learning. They might also overlook that retraining is not required for feature selection if importance is already established.
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
✓
Reduce the number of features by selecting the most important ones
To reduce inference latency without retraining the XGBoost model, reducing the number of features to the most important ones directly decreases the computational complexity of the model, as fewer tree splits are evaluated per request. This is a model-level optimization that does not require retraining if the feature importance is already known. SageMaker Elastic Inference, however, is designed to accelerate deep learning models by attaching a GPU accelerator; it does not speed up XGBoost or other tree-based models because they do not utilize GPUs effectively. Therefore, only option C is correct.
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 number of instances behind the endpoint
Why it's wrong here
Increasing the number of instances would distribute load but does not reduce per-request latency; it may even increase it due to overhead. Incorrect.
- ✗
Use SageMaker's batch transform instead of real-time endpoint
Why it's wrong here
Batch transform processes data asynchronously on a stored dataset, not in real time; the scenario requires a synchronous endpoint serving 100 requests per second with sub-200 ms latency, which batch transform cannot meet because it returns results only after the entire job completes. It is tempting because batch transform can reduce per-request overhead for large volumes of offline predictions, and would be correct if the company needed to score a static file of records without latency constraints.
- ✓
Reduce the number of features by selecting the most important ones
Why this is correct
Reducing to the most important features directly reduces model complexity and inference time without retraining. Correct.
- ✗
Use SageMaker's Elastic Inference to attach an acceleration to the endpoint
Why it's wrong here
SageMaker Elastic Inference is designed to accelerate deep learning models (e.g., TensorFlow, PyTorch) by attaching a GPU accelerator. It does not speed up tree-based models like XGBoost because they do not effectively utilize GPUs. Therefore, Option D is incorrect.
Go deeper
Related to this question
About these practice questions
One of 1,672 original MLS-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 MLS-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 MLS-C01 exam.