Which service should you use to handle class imbalance in training data?
Multiple choice — select one answer
Answer choices
Architectural breakdown & explanation
Imbalanced data requires sampling or weighted loss.
Correct answer(s): a. Oversampling, weights, or SMOTE techniques in SageMaker
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.