nerdexam
Google

PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #299

You have developed an AutoML tabular classification model that identifies high-value customers who interact with your organization's website. You plan to deploy the model to a new Vertex AI endpoint…

The correct answer is B. Configure the model deployment settings to use an n1-standard-4 machine type. Set the. This configuration allows you to optimize for both cost and performance. The n1-standard-4 machine type provides a good balance of resources for handling requests, while setting the minReplicaCount to 1 ensures that you always have at least one instance running to handle…

Submitted by jaden.t· Apr 18, 2026ML pipeline operationalization

Question

You have developed an AutoML tabular classification model that identifies high-value customers who interact with your organization's website. You plan to deploy the model to a new Vertex AI endpoint that will integrate with your website application. You expect higher traffic to the website during nights and weekends. You need to configure the model endpoint's deployment settings to minimize latency and cost. What should you do?

Options

  • AConfigure the model deployment settings to use an n1-standard-32 machine type.
  • BConfigure the model deployment settings to use an n1-standard-4 machine type. Set the
  • CConfigure the model deployment settings to use an n1-standard-4 machine type and a GPU
  • DConfigure the model deployment settings to use an n1-standard-8 machine type and a GPU

How the community answered

(32 responses)
  • A
    16% (5)
  • B
    75% (24)
  • C
    3% (1)
  • D
    6% (2)

Explanation

This configuration allows you to optimize for both cost and performance. The n1-standard-4 machine type provides a good balance of resources for handling requests, while setting the minReplicaCount to 1 ensures that you always have at least one instance running to handle traffic, and setting the maxReplicaCount to 8 allows for scaling up during peak traffic times (nights and weekends) to minimize latency. This setup helps manage costs effectively while ensuring the application can handle higher loads when necessary.

Topics

#Vertex AI Deployment#Model Endpoint Configuration#Resource Optimization#Tabular Models

Community Discussion

No community discussion yet for this question.

Sign up to join the discussion
Full PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice