nerdexam
Google

PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #169

You are a data scientist at an industrial equipment manufacturing company. You are developing a regression model to estimate the power consumption in the company's manufacturing plants based on sensor

The correct answer is B. Develop a regression model using BigQuery ML.. To schedule daily model training using tens of millions of daily records with minimal development, you should leverage BigQuery ML, which allows model training directly within BigQuery using SQL.

Submitted by miguelv· Apr 18, 2026ML pipeline operationalization

Question

You are a data scientist at an industrial equipment manufacturing company. You are developing a regression model to estimate the power consumption in the company's manufacturing plants based on sensor data collected from all of the plants. The sensors collect tens of millions of records every day. You need to schedule daily training runs for your model that use all the data collected up to the current date. You want your model to scale smoothly and require minimal development work. What should you do?

Options

  • ADevelop a custom TensorFlow regression model, and optimize it using Vertex AI Training.
  • BDevelop a regression model using BigQuery ML.
  • CDevelop a custom scikit-learn regression model, and optimize it using Vertex AI Training.
  • DDevelop a custom PyTorch regression model, and optimize it using Vertex AI Training.

How the community answered

(32 responses)
  • A
    3% (1)
  • B
    75% (24)
  • C
    16% (5)
  • D
    6% (2)

Why each option

To schedule daily model training using tens of millions of daily records with minimal development, you should leverage BigQuery ML, which allows model training directly within BigQuery using SQL.

ADevelop a custom TensorFlow regression model, and optimize it using Vertex AI Training.

Developing a custom TensorFlow model and optimizing it with Vertex AI Training requires significant development effort for model building, data preprocessing, and infrastructure management, which contradicts the goal of minimal development work.

BDevelop a regression model using BigQuery ML.Correct

BigQuery ML enables users to build and train machine learning models directly within BigQuery using standard SQL queries, which is ideal for very large datasets and aligns with the need for minimal development work as it abstracts underlying ML infrastructure. It scales inherently with BigQuery's data warehousing capabilities, making it suitable for daily training runs on extensive datasets.

CDevelop a custom scikit-learn regression model, and optimize it using Vertex AI Training.

Developing a custom scikit-learn model with Vertex AI Training involves substantial custom code and infrastructure configuration, making it a more complex and time-consuming solution compared to BigQuery ML for rapid development.

DDevelop a custom PyTorch regression model, and optimize it using Vertex AI Training.

Developing a custom PyTorch model with Vertex AI Training similarly demands considerable development overhead for model implementation and managed infrastructure, not aligning with the requirement for minimal development work.

Concept tested: BigQuery ML for large-scale, minimal-code ML

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

Topics

#BigQuery ML#Scalable ML#Regression Models#MLOps Automation

Community Discussion

No community discussion yet for this question.

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