How to deploy an existing BigQuery ML AutoML model for online prediction?

PMLE By islever Editorial Last updated

Short answer

C Alter the model by using BigQuery ML, and specify Vertex AI as the model registry. Deploy the model from Vertex AI Model Registry to a Vertex AI endpoint.

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?
  1. Retrain the model by using BigQuery ML, and specify Vertex AI as the model registry. Deploy the model from Vertex AI Model Registry to a Vertex AI endpoint,
  2. Retrain the model by using Vertex Al Deploy the model from Vertex AI Model. Registry to a Vertex AI endpoint.
  3. Alter the model by using BigQuery ML, and specify Vertex AI as the model registry. Deploy the model from Vertex AI Model Registry to a Vertex AI endpoint. Correct Answer
  4. Export the model from BigQuery ML to Cloud Storage. Import the model into Vertex AI Model Registry. Deploy the model to a Vertex AI endpoint.

Key Takeaways

The exam tests whether you know that BigQuery ML models can be registered into Vertex AI Model Registry via ALTER MODEL without exporting to Cloud Storage, and that retraining is unnecessary for an already-approved model.

The quickest way to deploy a trained BigQuery ML AutoML regression model for online prediction is to use the ALTER MODEL statement to register it directly with Vertex AI Model Registry, then deploy it to a Vertex AI endpoint—no retraining or Cloud Storage export required. Community consensus favors option C with 65 votes over D.

Common mistake: Option D is the most common wrong answer: exporting the model to Cloud Storage and importing it into Vertex AI. This is unnecessary because BigQuery ML natively supports registering models directly with Vertex AI Model Registry using ALTER MODEL, making the process faster and simpler.

Expert Analysis

Why the Answer Is Correct

Option C is correct because the model has already been trained and received positive feedback, so retraining (options A and B) is wasteful and slows deployment. The ALTER MODEL statement in BigQuery ML lets you update the model's metadata to specify Vertex AI as the model registry, effectively registering the existing model directly without needing to export it. As comment [6] notes, "retraining the model (A/B) is not necessary" and "exporting to Cloud Storage (D) is not necessary, since you can use the ALTER MODEL statement to register it on Vertex AI Model Registry." Community comments [2], [3], [5], and [10] all cite official documentation confirming this workflow.

Why the Other Options Are Wrong

Option A is wrong because it requires retraining the model, which is unnecessary and contradicts the goal of deploying as quickly as possible. Option B is wrong for the same reason and also uses Vertex AI training instead of BigQuery ML, adding complexity. Option D is wrong because, while it avoids retraining, it introduces an extra manual step of exporting to Cloud Storage and importing into Vertex AI; the direct ALTER MODEL registration in option C is faster and supported. Comment [3] explicitly states "no need to export the model," and comment [8] reinforces "No need to export the model to Cloud Storage."

Community Comment Notes

Several comments provide useful references: [2] links to the official ALTER MODEL syntax, [3] and [4] link to the BigQuery managing models in Vertex AI guide and the update_vertex page, and [10] links to registering a new BQML model version. Commenters who chose D (like [1] and [9]) incorrectly assumed that an export/import is required for Vertex AI online prediction, but the docs and the majority of comments clearly show the direct registration path. Comment [6] provides a concise summary that aligns with the correct answer and should be used as a quick review note.

Official Reference

These links open the official vendor documentation in a new tab.

Exam Strategy

When a question asks for the 'quickest' or 'as quickly as possible' deployment, always look for the option that avoids unnecessary retraining and extra export/import steps. Remember that BigQuery ML models can be registered directly to Vertex AI Model Registry via ALTER MODEL, so only choose export/import when the question explicitly requires a format change or offline model store.

Community Votes

C
67%
D
33%

67% of anonymous learners picked answer C. Votes are pick records left by other test-takers — they are not the verified answer.

Discussion 18 contributions

Compiled from public community threads and reader submissions, lightly edited for clarity. Handles and vote tallies are shown as recorded, and comments reflect the views of individual contributors.

From public community threads 18

  1. pikachu007 👍 7 Answered D
    I think it's D, as model retraining should not be required unless it's specified there's new data.
  2. cruise93 👍 6 Answered C
    https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-alter-model#alter_model_statement
  3. sonicclasps 👍 4 Answered C
    the answer is C, no need to export the model : "You can register BigQuery ML models with the Model Registry, in order to manage them alongside your other ML models without needing to export them" https://cloud.google.com/bigquery/docs/managing-models-vertex a simple update is sufficient : https://cloud.google.com/bigquery/docs/update_vertex
  4. gscharly 👍 3 Answered C
    https://cloud.google.com/vertex-ai/docs/model-registry/model-registry-bqml https://cloud.google.com/bigquery/docs/update_vertex
  5. fitri001 👍 2 Answered D
    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? A. Retrain the model by using BigQuery ML, and specify Vertex AI as the model registry. Deploy the model from Vertex AI Model Registry to a Vertex AI endpoint, B. Retrain the model by using Vertex Al Deploy the model from Vertex AI Model. Registry to a Vertex AI endpoint. C. Alter the model by using BigQuery ML, and specify Vertex AI as the model registry. Deploy the model from Vertex AI Model Registry to a Vertex AI endpoint. D. Export the model from BigQuery ML to Cloud Storage. Import the model into Vertex AI Model Registry. Deploy the model to a Vertex AI endpoint.
Show 13 more comments
  1. lunalongo 👍 2 Answered C
    C is the best option because: 1) Retraining the model (A/B) is not necessary (see positive feedbacks) 2) Exporting to Cloud Storage (D) is not necessary, since you can use the ALTER MODEL statement to register it on Vertex AI Model Registry and deploy it to the Vertex AI endpoint from there 3) Using BigQuery ML without exporting the model is the quickiest option
  2. phani49 👍 2 Answered C
    You can use the ALTER MODEL statement to register your existing BigQuery ML model with Vertex AI Model Registry https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-alter-model
  3. AzureDP900 👍 1
    C is correct Here's why: 1) You trained an AutoML regression model using BigQuery ML. 2)To deploy the model for online prediction, you need to export the model in a format that is compatible with Vertex AI. 3)Altering the model by using BigQuery ML and specifying Vertex AI as the model registry allows you to export the model in the correct format. Once exported, you can deploy the model from Vertex AI Model Registry to a Vertex AI endpoint, which enables online prediction
  4. alfieroy16 👍 1 Answered C
    Alter the model is correct,no need to export the model : "You can register BigQuery ML models with the Model Registry, in order to manage them alongside your other ML models without needing to export them" https://cloud.google.com/bigquery/docs/managing-models-vertex a simple update is sufficient : https://cloud.google.com/bigquery/docs/update_vertex
  5. lunalongo 👍 1
    D is the best option because: 1) BigQuery ML is excellent for training, not much for online prediction 2) Vertex AI provides a more robust and scalable infrastructure. 3) Exporting model from BigQuery ML to a format compatible with Vertex AI (typically Cloud Storage) is required
  6. vaibavi 👍 1 Answered B
    I think the answer here is B , because even if we alter or export automl regressor model trained in BQML is not supported in vertex ai for online prediction so we need to retrain using vertex ai
  7. omermahgoub 👍 1 Answered D
    D. Export the model from BigQuery ML to Cloud Storage. Import the model into Vertex AI Model Registry. Deploy the model to a Vertex AI endpoint.
  8. d6e1ae4 👍 1 Answered D
    The model has already been trained and received positive feedback, so there's no need to retrain the model.
  9. Land3r 👍 1 Answered C
    https://cloud.google.com/bigquery/docs/managing-models-vertex#register-new-bqml-model-version
  10. playerXL7 👍 1 Answered C
    https://cloud.google.com/vertex-ai/docs/model-registry/model-registry-bqml
  11. itwiz 👍 1
    C) https://cloud.google.com/bigquery/docs/create_vertex
  12. Omi_04040 👍 1 Answered C
    No need to export the model to Cloud Storage
  13. hybridpro 👍 1 Answered C
    It's C

Reader comments & corrections

No reader corrections yet — spotted an error or have a note? Share it below.

Log in to comment, report an error, or add a note about this question.

How to Minimize Development Time for Weekly TensorFlow Retraining in Vertex AI?

S-grade

How to Handle Categorical Features in BigQuery ML for Fast Deployment?

S-grade

How to preprocess BigQuery data for TensorFlow?

S-grade

How to Track Model and Prediction Lineage in Vertex AI?

S-grade

Practice All PMLE Questions

Access 65 questions with complete answers and detailed explanations.

View Full PMLE Practice Test →

← Back to PMLE Study Guide