nerdexam
Google

PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #98

You have been given a dataset with sales predictions based on your company's marketing activities. The data is structured and stored in BigQuery, and has been carefully managed by a team of data analy

The correct answer is A. Use BigQuery ML to run several regression models, and analyze their performance.. For rapid experimentation with various ML models on structured data in BigQuery, BigQuery ML offers the most efficient and self-serviced solution, directly leveraging the existing data.

Submitted by haruto_sh· Apr 18, 2026ML model development

Question

You have been given a dataset with sales predictions based on your company's marketing activities. The data is structured and stored in BigQuery, and has been carefully managed by a team of data analysts. You need to prepare a report providing insights into the predictive capabilities of the data. You were asked to run several ML models with different levels of sophistication, including simple models and multilayered neural networks. You only have a few hours to gather the results of your experiments. Which Google Cloud tools should you use to complete this task in the most efficient and self-serviced way?

Options

  • AUse BigQuery ML to run several regression models, and analyze their performance.
  • BRead the data from BigQuery using Dataproc, and run several models using SparkML.
  • CUse Vertex AI Workbench user-managed notebooks with scikit-learn code for a variety of ML
  • DTrain a custom TensorFlow model with Vertex AI, reading the data from BigQuery featuring a

How the community answered

(31 responses)
  • A
    81% (25)
  • B
    10% (3)
  • C
    6% (2)
  • D
    3% (1)

Why each option

For rapid experimentation with various ML models on structured data in BigQuery, BigQuery ML offers the most efficient and self-serviced solution, directly leveraging the existing data.

AUse BigQuery ML to run several regression models, and analyze their performance.Correct

BigQuery ML (BQML) allows users to train and evaluate a variety of models, including regression models, directly within BigQuery using SQL. This approach is highly efficient and self-serviced as it avoids data movement and complex setup, enabling quick experimentation and performance analysis within a few hours.

BRead the data from BigQuery using Dataproc, and run several models using SparkML.

Using Dataproc and SparkML introduces overhead for cluster management and requires writing Spark code, making it less self-serviced and efficient for this use case than BQML.

CUse Vertex AI Workbench user-managed notebooks with scikit-learn code for a variety of ML

Vertex AI Workbench notebooks with scikit-learn would require moving data out of BigQuery into the notebook environment, which can be inefficient for large datasets and adds setup complexity compared to BQML.

DTrain a custom TensorFlow model with Vertex AI, reading the data from BigQuery featuring a

Training a custom TensorFlow model with Vertex AI involves significant development effort in custom code and architecture, contradicting the need for efficiency and self-service to run several models quickly.

Concept tested: Google Cloud ML tools for rapid prototyping on structured data

Source: https://cloud.google.com/bigquery-ml/docs/introduction

Topics

#BigQuery ML#Rapid Prototyping#Self-service ML#Model Selection

Community Discussion

No community discussion yet for this question.

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