A manufacturing company wants to run a defect-detection model on cameras installed at each factory line. The model must make predictions locally with no internet connection. Which deployment strategy should they use?

Serverless deployment with AWS Lambda

Real-time deployment with a REST API in the cloud

Edge deployment on the cameras or local gateways

A data science team uses MLflow to manage models. They have multiple models in the registry, and they need to ensure that the production endpoint always serves the latest approved version. They also need to roll back quickly if the new version fails. What is the BEST approach?

Deploy every model version to a separate endpoint and update the application to point to the latest

Manually update the model file in the container image

Use MLflow model registry stages and deploy the model in 'Production' stage, with a rollback plan to the previous 'Production' version

Use MLflow Projects to deploy the model

CertNexusCertified Data Science Practitioner (CDSP)

Domain 6Objective 2

Deploy and Manage Models CERTIFIED-DATA-SCIENCE-PRACTITIONER Practice Questions (Page 1)

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 1–5

1foundation · easy
In Azure Machine Learning, which component is used to expose a trained model as a REST API for real-time inference?
Select an answer first
2foundation · easy
In Kubeflow, which component is used to define and run a multi-step machine learning workflow, such as data preprocessing, training, and evaluation?
Select an answer first
3application · medium
A manufacturing company wants to run a defect-detection model on cameras installed at each factory line. The model must make predictions locally with no internet connection. Which deployment strategy should they use?
Select an answer first
4application · medium
A financial services firm deploys a fraud-detection model that must return a decision in under 100 milliseconds. The team expects traffic to double during holiday sales. Which production consideration is MOST critical to address during deployment?
Select an answer first
5expert · hard
A data science team uses MLflow to manage models. They have multiple models in the registry, and they need to ensure that the production endpoint always serves the latest approved version. They also need to roll back quickly if the new version fails. What is the BEST approach?
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 1)

Questions 1–5

In Azure Machine Learning, which component is used to expose a trained model as a REST API for real-time inference?

In Kubeflow, which component is used to define and run a multi-step machine learning workflow, such as data preprocessing, training, and evaluation?

A manufacturing company wants to run a defect-detection model on cameras installed at each factory line. The model must make predictions locally with no internet connection. Which deployment strategy should they use?

A financial services firm deploys a fraud-detection model that must return a decision in under 100 milliseconds. The team expects traffic to double during holiday sales. Which production consideration is MOST critical to address during deployment?

A data science team uses MLflow to manage models. They have multiple models in the registry, and they need to ensure that the production endpoint always serves the latest approved version. They also need to roll back quickly if the new version fails. What is the BEST approach?

Keep studying — 6.0 Operationalizing the pipeline