MLA-C01 ML Model Development Practice Question
A company uses SageMaker Clarify to detect bias in their training data. They find that the model has a high disparate impact for a protected attribute. What should they do to mitigate this bias during training?
⚠ Common exam trap
MLA-C01 often tests the misconception that SageMaker Clarify can automatically mitigate bias during training, when in fact it only detects and explains bias; mitigation requires separate preprocessing, in-processing, or post-processing techniques.
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
✓
Preprocess the data using techniques like reweighing or resampling to reduce bias
SageMaker Clarify detects bias but does not automatically mitigate it during training. To reduce disparate impact, the correct approach is to preprocess the training data using bias mitigation techniques such as reweighing (assigning weights to instances to balance outcomes across groups) or resampling (oversampling underrepresented groups or undersampling overrepresented ones). These methods adjust the data distribution before training, directly addressing the source of bias and reducing disparate impact.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Use SageMaker Clarify’s built-in bias mitigation algorithm during training
Why it's wrong here
SageMaker Clarify detects and reports bias metrics; it does not provide a built-in training-time mitigation algorithm that adjusts the model. It is tempting because Clarify already surfaces the disparate impact, but mitigation requires techniques such as reweighting or adversarial debiasing applied in the training code.
- ✗
Remove the protected attribute from the dataset
Why it's wrong here
Dropping the protected attribute does not remove bias, because correlated proxy features encode the same information and disparate impact persists. It is tempting as a simple fairness fix, but the correct approach applies bias mitigation during training, such as reweighting or adversarial debiasing, rather than deleting the column.
- ✗
Increase the model complexity to capture more patterns
Why it's wrong here
Raising model complexity increases capacity to fit patterns, including the proxy correlations driving disparate impact, so bias typically worsens rather than mitigates. Complexity tuning is tempting when accuracy is poor, but here the requirement is reducing disparity, which SageMaker Clarify's bias mitigation or reweighting addresses during training.
- ✓
Preprocess the data using techniques like reweighing or resampling to reduce bias
Why this is correct
Reweighing assigns weights to training examples so the protected and unprotected groups contribute proportionally, while resampling adjusts class balance. Applied before training, these preprocessing techniques reduce the disparate impact measured by SageMaker Clarify at its source.
Go deeper
Related to this question
About these practice questions
Courseiva writes every MLA-C01 question from scratch — 665 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Amazon Web Services exam blueprint
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.