nerdexam
Google

PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #247

You work for a large retailer, and you need to build a model to predict customer chum. The company has a dataset of historical customer data, including customer demographics purchase history, and webs

The correct answer is B. Create a logistic regression model in BigQuery ML and register the model in Vertex AI Model. To predict customer churn, which is a binary classification problem, using BigQuery ML, create a logistic regression model, and register it with Vertex AI Model Registry for lifecycle management.

Submitted by neha2k· Apr 18, 2026ML pipeline operationalization

Question

You work for a large retailer, and you need to build a model to predict customer chum. The company has a dataset of historical customer data, including customer demographics purchase history, and website activity. You need to create the model in BigQuery ML and thoroughly evaluate its performance. What should you do?

Options

  • ACreate a linear regression model in BigQuery ML, and register the model in Vertex AI Model
  • BCreate a logistic regression model in BigQuery ML and register the model in Vertex AI Model
  • CCreate a linear regression model in BigQuery ML. Use the ML.EVALUATE function to evaluate
  • DCreate a logistic regression model in BigQuery ML. Use the ML.CONFUSION_MATRIX function

How the community answered

(27 responses)
  • A
    11% (3)
  • B
    78% (21)
  • C
    7% (2)
  • D
    4% (1)

Why each option

To predict customer churn, which is a binary classification problem, using BigQuery ML, create a logistic regression model, and register it with Vertex AI Model Registry for lifecycle management.

ACreate a linear regression model in BigQuery ML, and register the model in Vertex AI Model

Linear regression is used for predicting continuous numerical values, not binary outcomes like churn.

BCreate a logistic regression model in BigQuery ML and register the model in Vertex AI ModelCorrect

Customer churn prediction is a binary classification problem (churn or not churn), for which logistic regression is an appropriate algorithm. Creating the model in BigQuery ML is straightforward, and registering it in Vertex AI Model Registry enables centralized model management and deployment.

CCreate a linear regression model in BigQuery ML. Use the ML.EVALUATE function to evaluate

Linear regression is incorrect for churn prediction, as it's designed for continuous target variables, not binary classification.

DCreate a logistic regression model in BigQuery ML. Use the ML.CONFUSION_MATRIX function

While `ML.CONFUSION_MATRIX` is useful for evaluating classification models, it's typically part of the broader `ML.EVALUATE` function and this option omits the crucial step of registering the model in Vertex AI Model Registry.

Concept tested: BigQuery ML model selection for classification, model evaluation, and registration

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

Topics

#Logistic Regression#BigQuery ML#Customer Churn Prediction#Vertex AI Model Registry

Community Discussion

No community discussion yet for this question.

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