CoursesFree Quizzes
Google CloudArchitecting low-code AI solutions

Automl & Vertex AI — PMLE Practice Question

A representative Google Cloud Professional Machine Learning Engineer (PMLE) exam question on Automl & Vertex AI. Work through it below, then read why each option is right or wrong.

This question is part of the free Google Cloud Professional Machine Learning Engineer practice test.

Short answer

The correct answer is B. Run a Vertex AI AutoML Tabular training job pointed directly at the BigQuery table, letting Vertex AI perform automatic architecture search and hyperparameter tuning.

Vertex AI AutoML Tabular can train directly from a BigQuery source table and performs automatic model architecture search and hyperparameter tuning without any custom training code, and the resulting model registers in Vertex AI Model Registry for straightforward endpoint deployment, matching every stated requirement. Creating a logistic regression model in BigQuery ML with manually specified hyperparameters requires the manual tuning effort the team wants to avoid and performs no architecture search. Writing a custom Keras script for a Vertex AI Training job requires exactly the custom training code the team wants to avoid, along with exporting data out of BigQuery first. A BigQuery ML boosted tree classifier with default hyperparameters uses a fixed algorithm with no automatic architecture search or tuning process, so it does not satisfy the automatic-tuning requirement.

The Question

An ML engineer has structured customer data in a BigQuery table and must build a churn-prediction classification model. The team wants automatic model architecture search and hyperparameter tuning with no custom training code, and wants the resulting model to be easily registered and deployed to a Vertex AI endpoint for online predictions. Which approach best meets these requirements?

AExport the table to Cloud Storage and write a custom Keras training script to run as a Vertex AI Training custom job
BRun a Vertex AI AutoML Tabular training job pointed directly at the BigQuery table, letting Vertex AI perform automatic architecture search and hyperparameter tuningCorrect
CCreate a BigQuery ML model with CREATE MODEL using BOOSTED_TREE_CLASSIFIER and default hyperparameters
DCreate a BigQuery ML model with CREATE MODEL using LOGISTIC_REG and manually specified hyperparameter values

Why B is correct

Vertex AI AutoML Tabular can train directly from a BigQuery source table and performs automatic model architecture search and hyperparameter tuning without any custom training code, and the resulting model registers in Vertex AI Model Registry for straightforward endpoint deployment, matching every stated requirement. Creating a logistic regression model in BigQuery ML with manually specified hyperparameters requires the manual tuning effort the team wants to avoid and performs no architecture search. Writing a custom Keras script for a Vertex AI Training job requires exactly the custom training code the team wants to avoid, along with exporting data out of BigQuery first. A BigQuery ML boosted tree classifier with default hyperparameters uses a fixed algorithm with no automatic architecture search or tuning process, so it does not satisfy the automatic-tuning requirement.

Why the other options are wrong

Option A: Export the table to Cloud Storage and write a custom Keras training script to run as a Vertex AI Training custom job

Option A does not satisfy the requirement in the scenario. Review the explanation above: the correct choice (B) is the only one that fully meets every constraint stated in the question.

Option C: Create a BigQuery ML model with CREATE MODEL using BOOSTED_TREE_CLASSIFIER and default hyperparameters

Option C does not satisfy the requirement in the scenario. Review the explanation above: the correct choice (B) is the only one that fully meets every constraint stated in the question.

Option D: Create a BigQuery ML model with CREATE MODEL using LOGISTIC_REG and manually specified hyperparameter values

Option D does not satisfy the requirement in the scenario. Review the explanation above: the correct choice (B) is the only one that fully meets every constraint stated in the question.

Key idea: Automl & Vertex AI

Vertex AI AutoML Tabular can train directly from a BigQuery source table and performs automatic model architecture search and hyperparameter tuning without any custom training code, and the resulting model registers in Vertex AI Model Registry for straightforward endpoint deployment, matching every stated requirement. Creating a logistic regression model in BigQuery ML with manually specified hyperparameters requires the manual tuning effort the team wants to avoid and performs no architecture search. Writing a custom Keras script for a Vertex AI Training job requires exactly the custom training code the team wants to avoid, along with exporting data out of BigQuery first. A BigQuery ML boosted tree classifier with default hyperparameters uses a fixed algorithm with no automatic architecture search or tuning process, so it does not satisfy the automatic-tuning requirement. On the PMLE exam, questions in the "Architecting low-code AI solutions" domain test whether you can map a scenario's constraints to the right choice. Read the requirement carefully, eliminate options that violate any single constraint, and pick the one that satisfies all of them with the least operational overhead.

Ready to see how you'd score?

Take the free practice quiz and find out which Google Cloud Professional Machine Learning Engineer domains you need to focus on. No signup required.

Take the free quizSee all 207+ practice questions

Practice 5 similar questions

Same cert, same or adjacent domain. Use these after reviewing the explanation.

1Experiment Tracking & ML Metadata — PMLE Practice QuestionCollaborating to manage data and models2Hyperparameter Tuning & Foundation Models — PMLE Practice QuestionScaling prototypes into ML models3Vertex AI & Online Inference — PMLE Practice QuestionServing and scaling models4Feature Engineering & Transformation Consistency — PMLE Practice QuestionAutomating and orchestrating ML pipelines5Responsible AI & Bias Detection — PMLE Practice QuestionMonitoring AI solutions

Related Google Cloud Professional Machine Learning Engineer Practice Questions

Experiment Tracking & ML Metadata — PMLE Practice Question→Hyperparameter Tuning & Foundation Models — PMLE Practice Question→Vertex AI & Online Inference — PMLE Practice Question→

Official sources used

Verify program and exam details at the source before scheduling.

cloud.google.comE2e Automl