A company deploys a real-time recommendation model on AWS SageMaker. The model's latency is acceptable, but the team notices that the model's performance degrades over time as customer behavior changes. They need to detect this issue early and retrain the model. Which combination of actions should they take?

Manually retrain the model every month

Set up SageMaker Model Monitor to track data drift and trigger a retraining pipeline when drift is detected

Increase the endpoint's instance count to handle more traffic

Use SageMaker Ground Truth to label new data

CertNexusCertified Data Science Practitioner (CDSP)

Domain 6Objective 2

Deploy and Manage Models CERTIFIED-DATA-SCIENCE-PRACTITIONER Practice Questions (Page 7)

Part of the 6.0 Operationalizing the pipeline domain, which accounts for 5-8% of the CERTIFIED-DATA-SCIENCE-PRACTITIONER exam.

36questions here

8free pages

8concepts

5-8%of the exam

Questions 31–35

31foundation · easy
A data scientist wants to log parameters, metrics, and artifacts from a training run so they can compare different experiments later. Which MLflow component is designed for this purpose?
Select an answer first
32foundation · easy
A team wants to deploy two versions of a model to the same SageMaker endpoint and gradually shift traffic from the old version to the new one. Which SageMaker feature enables this?
Select an answer first
33foundation · easy
A retail company wants to deploy a product recommendation model directly on in-store kiosks so that recommendations are generated locally even if the store's internet connection is temporarily unavailable. Which deployment strategy is most appropriate?
Select an answer first
34expert · hard
A company deploys a real-time recommendation model on AWS SageMaker. The model's latency is acceptable, but the team notices that the model's performance degrades over time as customer behavior changes. They need to detect this issue early and retrain the model. Which combination of actions should they take?
Select an answer first
35foundation · easy
In AWS SageMaker, which component provides a persistent HTTPS endpoint that applications can call to get real-time predictions from a deployed model?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to CERTIFIED-DATA-SCIENCE-PRACTITIONER

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by CertNexus. “CERTIFIED-DATA-SCIENCE-PRACTITIONER” is a trademark of its owner, used for identification only.

Deploy and Manage Models CERTIFIED-DATA-SCIENCE-PRACTITIONER Practice Questions (Page 7)

Questions 31–35

A data scientist wants to log parameters, metrics, and artifacts from a training run so they can compare different experiments later. Which MLflow component is designed for this purpose?

A team wants to deploy two versions of a model to the same SageMaker endpoint and gradually shift traffic from the old version to the new one. Which SageMaker feature enables this?

A retail company wants to deploy a product recommendation model directly on in-store kiosks so that recommendations are generated locally even if the store's internet connection is temporarily unavailable. Which deployment strategy is most appropriate?

In AWS SageMaker, which component provides a persistent HTTPS endpoint that applications can call to get real-time predictions from a deployed model?

Keep studying — 6.0 Operationalizing the pipeline