nerdexam
Google

PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #278

You created a model that uses BigQuery ML to perform linear regression. You need to retrain the model on the cumulative data collected every week. You want to minimize the development effort and the s

The correct answer is A. Use BigQuery's scheduling service to run the model retraining query periodically.. To efficiently retrain a BigQuery ML linear regression model weekly on cumulative data with minimal development effort and scheduling cost, use BigQuery's native scheduling service.

Submitted by eva_at· Apr 18, 2026ML pipeline operationalization

Question

You created a model that uses BigQuery ML to perform linear regression. You need to retrain the model on the cumulative data collected every week. You want to minimize the development effort and the scheduling cost. What should you do?

Options

  • AUse BigQuery's scheduling service to run the model retraining query periodically.
  • BCreate a pipeline in Vertex AI Pipelines that executes the retraining query, and use the Cloud
  • CUse Cloud Scheduler to trigger a Cloud Function every week that runs the query for retraining the
  • DUse the BigQuery API Connector and Cloud Scheduler to trigger Workflows every week that

How the community answered

(39 responses)
  • A
    77% (30)
  • B
    3% (1)
  • C
    8% (3)
  • D
    13% (5)

Why each option

To efficiently retrain a BigQuery ML linear regression model weekly on cumulative data with minimal development effort and scheduling cost, use BigQuery's native scheduling service.

AUse BigQuery's scheduling service to run the model retraining query periodically.Correct

Since the model is a BigQuery ML model and retraining involves running a query, using BigQuery's built-in scheduling service is the most straightforward and cost-effective solution. This minimizes development effort by leveraging native BigQuery functionality to run queries periodically without external orchestration services.

BCreate a pipeline in Vertex AI Pipelines that executes the retraining query, and use the Cloud

While Vertex AI Pipelines can orchestrate ML workflows, for a simple periodic retraining of a BigQuery ML model (which is essentially a SQL query), it introduces unnecessary complexity and overhead compared to BigQuery's native scheduling.

CUse Cloud Scheduler to trigger a Cloud Function every week that runs the query for retraining the

Using Cloud Scheduler to trigger a Cloud Function to run a BigQuery query adds an extra layer of complexity and service invocation overhead compared to BigQuery's direct query scheduling, increasing development effort and potential cost.

DUse the BigQuery API Connector and Cloud Scheduler to trigger Workflows every week that

This option involves multiple external services (BigQuery API Connector, Cloud Scheduler, Workflows) to achieve a task that BigQuery's native scheduling can handle directly and more simply, thus increasing development effort and potential cost.

Concept tested: BigQuery ML scheduled queries

Source: https://cloud.google.com/bigquery/docs/scheduling-queries

Topics

#BigQuery ML#Model Retraining#Scheduling#Cost Optimization

Community Discussion

No community discussion yet for this question.

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