nerdexam
Google

PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #300

You developed a BigQuery ML linear regressor model by using a training dataset stored in a BigQuery table. New data is added to the table every minute. You are using Cloud Scheduler and Vertex AI Pipe

The correct answer is B. Use the TRANSFORM clause in the CREATE MODEL statement in the SQL query to calculate the. Using the TRANSFORM clause allows you to apply preprocessing steps directly within the model training process. This means that the required statistics for quantile bucketization and MinMax scaling can be calculated on-the-fly during model training and inference, minimizing storag

Submitted by yuriko_h· Apr 18, 2026Data processing and feature engineering

Question

You developed a BigQuery ML linear regressor model by using a training dataset stored in a BigQuery table. New data is added to the table every minute. You are using Cloud Scheduler and Vertex AI Pipelines to automate hourly model training, and use the model for direct inference. The feature preprocessing logic includes quantile bucketization and MinMax scaling on data received in the last hour. You want to minimize storage and computational overhead. What should you do?

Options

  • APreprocess and stage the data in BigQuery prior to feeding it to the model during training and
  • BUse the TRANSFORM clause in the CREATE MODEL statement in the SQL query to calculate the
  • CCreate a component in the Vertex AI Pipelines directed acyclic graph (DAG) to calculate the
  • DCreate SQL queries to calculate and store the required statistics in separate BigQuery tables that

How the community answered

(50 responses)
  • A
    10% (5)
  • B
    82% (41)
  • C
    2% (1)
  • D
    6% (3)

Explanation

Using the TRANSFORM clause allows you to apply preprocessing steps directly within the model training process. This means that the required statistics for quantile bucketization and MinMax scaling can be calculated on-the-fly during model training and inference, minimizing storage overhead by not requiring separate tables to store these statistics. This approach also streamlines the workflow by integrating the preprocessing into the model training SQL query, thus reducing computational overhead and complexity in your pipeline.

Topics

#BigQuery ML#Feature Engineering#Data Preprocessing#Resource Optimization

Community Discussion

No community discussion yet for this question.

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