A company is using an Amazon SageMaker AI ML model to predict traffic accidents that potholes cause. An ML engineer has configured SageMaker Model Monitor to run as part of a SageMaker AI pipeline…

Question

Options

• ARetrain the model by using a new SageMaker AI training job. Check for errors by using
• BRetrain the model with new training data. Reuse the original baseline in Model Monitor.
• CRetrain the model with new training data. Use the new baseline in Model Monitor.
• DRerun the SageMaker AI pipeline after enabling the emit_metrics option in the baseline

• A
  15% (4)
• B
  7% (2)
• C
  74% (20)
• D
  4% (1)

Explanation

The correct answer is C. Baseline drift violations in SageMaker Model Monitor indicate that the current data distribution has shifted significantly from the original baseline used to define 'normal.' This typically means the real-world data has changed (e.g., new pothole patterns or road conditions). The correct fix is to retrain the model with fresh, representative data and then re-establish a new baseline in Model Monitor that reflects the updated data distribution. Option B reuses the old baseline, which would continue to produce drift violations. Option A does not address the data distribution shift. Option D's emit_metrics flag does not resolve underlying data drift.

No community discussion yet for this question.