nerdexam
Google

PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #257

You recently used BigQuery ML to train an AutoML regression model. You shared results with your team and received positive feedback. You need to deploy your model for online prediction as quickly as p

The correct answer is D. Export the model from BigQuery ML to Cloud Storage. Import the model into Vertex AI Model. To quickly deploy a BigQuery ML AutoML regression model for online prediction, export the model to Cloud Storage, then import it into Vertex AI Model Registry, and deploy it to a Vertex AI endpoint.

Submitted by haru.x· Apr 18, 2026ML pipeline operationalization

Question

You recently used BigQuery ML to train an AutoML regression model. You shared results with your team and received positive feedback. You need to deploy your model for online prediction as quickly as possible. What should you do?

Options

  • ARetrain the model by using BigQuery ML, and specify Vertex AI as the model registry. Deploy the
  • BRetrain the model by using Vertex Al Deploy the model from Vertex AI Model. Registry to a
  • CAlter the model by using BigQuery ML, and specify Vertex AI as the model registry. Deploy the
  • DExport the model from BigQuery ML to Cloud Storage. Import the model into Vertex AI Model

How the community answered

(30 responses)
  • A
    3% (1)
  • B
    7% (2)
  • C
    10% (3)
  • D
    80% (24)

Why each option

To quickly deploy a BigQuery ML AutoML regression model for online prediction, export the model to Cloud Storage, then import it into Vertex AI Model Registry, and deploy it to a Vertex AI endpoint.

ARetrain the model by using BigQuery ML, and specify Vertex AI as the model registry. Deploy the

Retraining the model in BigQuery ML, even if specifying Vertex AI as the registry, would consume additional time and resources, delaying the quick deployment.

BRetrain the model by using Vertex Al Deploy the model from Vertex AI Model. Registry to a

Retraining the model using Vertex AI would be a completely new training process, delaying deployment significantly and not leveraging the existing BigQuery ML model.

CAlter the model by using BigQuery ML, and specify Vertex AI as the model registry. Deploy the

The `ALTER MODEL` statement in BigQuery ML is used for tasks like setting default options, not for migrating a model to Vertex AI or deploying it directly.

DExport the model from BigQuery ML to Cloud Storage. Import the model into Vertex AI ModelCorrect

BigQuery ML models, including AutoML regression models, can be exported to Cloud Storage. Once in Cloud Storage, they can be imported into Vertex AI Model Registry and subsequently deployed to a Vertex AI endpoint for low-latency online predictions, which is the fastest path to production for models trained in BQML.

Concept tested: Deploying BigQuery ML models to Vertex AI for online prediction

Source: https://cloud.google.com/bigquery-ml/docs/export-model-overview

Topics

#BigQuery ML#Vertex AI#Model Deployment#Online Prediction

Community Discussion

No community discussion yet for this question.

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