AWS Certified AI Practitioner (AIF-C01) — Question 279

A company is monitoring a predictive model by using Amazon SageMaker Model Monitor. The company notices data drift beyond a defined threshold. The company wants to mitigate a potentially adverse impact on the predictive model.

Which solution will meet these requirements?

Answer options

• A. Restart the SageMaker AI endpoint.
• B. Adjust the monitoring sensitivity.
• C. Re-train the model with fresh data.
• D. Set up experiments tracking.

Correct answer: C

Explanation

Data drift indicates that the distribution of real-world inference data has deviated from the original dataset used for training, which can lead to degraded model performance over time. To resolve this issue, the model must be re-trained with fresh, up-to-date data that accurately represents the new data distribution. Other actions, such as restarting the endpoint or adjusting monitoring thresholds, only mask the issue or address infrastructure instead of resolving the underlying model inaccuracy.