MLA-C01 Domain 1: Data Preparation for Machine Learning

After a design review, leadership requires the team to anonymize PII before model training. Which approach is MOST reliable? anonymize PII before model training.

Multiple choice — select one answer

Answer choices

  1. a. Amazon SageMaker Data Wrangler
  2. b. AWS Glue Data Catalog and crawlers
  3. c. SageMaker Ground Truth
  4. d. Amazon Macie + transformation jobs

Architectural breakdown & explanation

Remove or tokenize sensitive attributes early.

Correct answer(s): d. Amazon Macie + transformation jobs

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.