Crucial Exams

GCP Professional Data Engineer Practice Question

A retail analytics team wants to build a BigQuery ML churn-prediction model directly on a raw transactions table. They need to scale continuous column spend_amount to a range and convert the categorical column membership_tier into separate binary indicators. The team prefers not to create intermediate tables or views and wants preprocessing to be applied consistently during both training and online prediction. Which approach best meets these requirements in BigQuery ML?

  • Create the model with a TRANSFORM clause that calls ML.NORMALIZER(spend_amount) and ML.ONE_HOT_ENCODER(membership_tier); BigQuery ML will learn the scaling parameters during training and re-apply them during prediction.

  • Build a materialized view that performs the scaling and one-hot encoding, then point CREATE MODEL at the view so preprocessing happens outside the model.

  • Store the raw table in Vertex AI Feature Store and configure a feature-engineering pipeline; reference the resulting feature view from BigQuery ML during training and serving.

  • Run a scheduled UPDATE query that rewrites the training table with normalized and encoded columns before each CREATE MODEL statement.

GCP Professional Data Engineer
Preparing and using data for analysis
Your Score:
Settings & Objectives
Random Mixed
Questions are selected randomly from all chosen topics, with a preference for those you haven’t seen before. You may see several questions from the same objective or domain in a row.
Rotate by Objective
Questions cycle through each objective or domain in turn, helping you avoid long streaks of questions from the same area. You may see some repeat questions, but the distribution will be more balanced across topics.

Check or uncheck an objective to set which questions you will receive.

Wipe Score
Bash, the Crucial Exams Chat Bot
AI Bot