MLA-C01 Domain 1: Data Preparation for Machine Learning

Which service should you use to run ETL on large datasets in a data lake?

Multiple choice — select one answer

Answer choices

  1. a. SageMaker Processing or sklearn split with stratification
  2. b. Oversampling, weights, or SMOTE techniques in SageMaker
  3. c. SageMaker Ground Truth
  4. d. AWS Glue

Architectural breakdown & explanation

Glue provides serverless Spark ETL.

Correct answer(s): d. AWS Glue

Exam domain: Domain 1: Data Preparation for Machine Learning (28% weight on the official guide).

Official documentation & study links

Practice this certification

This page is one question from the AWS Certified Machine Learning Engineer – Associate bank. Run a full timed practice exam with domain-weighted random questions in your browser.