Should Customer Churn Models Use BigQuery ML or Vertex AI for Evaluation?

PMLE By islever Editorial Last updated

Short answer

B Create a logistic regression model in BigQuery ML and register the model in Vertex AI Model Registry. Evaluate the model performance in Vertex AI .

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?
  1. Create a linear regression model in BigQuery ML, and register the model in Vertex AI Model Registry. Evaluate the model performance in Vertex AI .
  2. Create a logistic regression model in BigQuery ML and register the model in Vertex AI Model Registry. Evaluate the model performance in Vertex AI . Correct Answer
  3. Create a linear regression model in BigQuery ML. Use the ML.EVALUATE function to evaluate the model performance.
  4. Create a logistic regression model in BigQuery ML. Use the ML.CONFUSION_MATRIX function to evaluate the model performance.

Key Takeaways

The exam question tests whether you recognize that churn prediction is a binary classification problem and that Vertex AI provides the more thorough evaluation required by the phrase 'thoroughly evaluate its performance'.

For customer churn prediction in BigQuery ML, the community strongly supports using logistic regression and registering the model in Vertex AI Model Registry for thorough evaluation; BigQuery ML evaluation functions like ML.CONFUSION_MATRIX are useful but less comprehensive.

Common mistake: Choosing D because it correctly uses logistic regression and ML.CONFUSION_MATRIX. The trap is that a confusion matrix alone is only one evaluation tool, and 'thoroughly evaluate' points to Vertex AI for richer metrics, tracking, and model management.

Expert Analysis

Why the Answer Is Correct

Customer churn prediction is inherently a binary classification problem: each customer either churns or does not. Logistic regression is the appropriate BigQuery ML model type, so option B is the only one that combines the correct model and the right evaluation approach. The phrase 'thoroughly evaluate its performance' points to Vertex AI, which offers more comprehensive metrics, experiment tracking, and model versioning than BigQuery ML alone. Comment [1] captures this succinctly: use logistic regression because it is classification, and use Vertex AI because we need to thoroughly evaluate performance. Comment [3] reinforces that Vertex AI is the definitive answer because it supports more than just a single evaluation function.

Why the Other Options Are Wrong

Options A and C use linear regression, which is designed for continuous numeric prediction, not binary classification like churn, so they are immediately incorrect. Option C also lacks Vertex AI evaluation, but the wrong model type is its primary flaw. Option D correctly selects logistic regression and uses ML.CONFUSION_MATRIX, but a confusion matrix is only one piece of the evaluation puzzle. As comment [3] notes, using the confusion matrix is not wrong, but it is not enough if you want to thoroughly evaluate model performance. Therefore, B is the better answer because Vertex AI provides a broader set of evaluation and model management capabilities.

Community Comment Notes

The vote distribution is 82 for B versus 18 for D, showing strong consensus for Vertex AI. Comment [2] offers an interesting nuance: even if churn might be viewed as a numeric count, the standard interpretation is classification, and Vertex AI is better suited for thorough evaluation. Comment [6] also agrees that the phrase 'thoroughly evaluate' suggests a more comprehensive approach than a single BigQuery ML function. Comment [7] links to the official Vertex AI evaluation documentation, reinforcing that Vertex AI has dedicated classification evaluation features. The community consistently identifies that BigQuery ML's ML.CONFUSION_MATRIX alone is insufficient for the requirement, making option B the best fit.

Official Reference

These links open the official vendor documentation in a new tab.

Exam Strategy

Look for signal words: 'churn' signals binary classification, so immediately eliminate linear regression options; 'thoroughly evaluate' signals that Vertex AI is required over a single BigQuery ML function. When both a valid BigQuery ML evaluation and a Vertex AI option appear, choose the Vertex AI option for comprehensive evaluation.

Community Votes

B
82%
D
18%

82% of anonymous learners picked answer B. Votes are pick records left by other test-takers — they are not the verified answer.

Discussion 7 contributions

Compiled from public community threads and reader submissions, lightly edited for clarity. Handles and vote tallies are shown as recorded, and comments reflect the views of individual contributors.

From public community threads 7

  1. b1a8fae 👍 4 Answered B
    B. Linear regression because customer churn is a number of customers (not just 1/0). The key here imo is "thoroughly evaluate performance", which Vertex AI seems to be better suited for than BQ (including the possibility of tracking experiment lineage, inspecting parameter selection of each run, etc)
  2. gscharly 👍 4 Answered B
    logistic since it's classification, and Vertex AI because we need to "thoroughly evaluate its performance"
  3. Dirtie_Sinkie 👍 3 Answered B
    B is the definitive answer. By breaking down the question we know it is a classification problem, so A and C are wrong since they're linear regression. Using confusion matrix to evaluate the model is not wrong (actually it's even the textbook answer to do it), but it is not enough if you want to thoroughly evaluate its performance. Hence the best way to do it is with Vertex AI.
  4. pikachu007 👍 3 Answered D
    Customer churn prediction involves a binary classification task (whether a customer will churn or not). Logistic regression is specifically designed for this type of problem, making it the appropriate model. BigQuery ML allows building and training logistic regression models directly within BigQuery, leveraging its scalability and SQL-like syntax for model development.
  5. fitri001 👍 1 Answered B
    Logistic Regression: While linear regression (option C) can be used for continuous prediction tasks, customer churn is a binary classification problem (churned/not churned). Logistic regression is a better fit for this scenario. Vertex AI Model Registry: Registering the model in Vertex AI Model Registry provides a centralized location for model management, versioning, and potentially future deployment to other Vertex AI services. Vertex AI Evaluation: Vertex AI offers more comprehensive evaluation tools than BigQuery ML's ML.EVALUATE function (option C) or ML.CONFUSION_MATRIX function (option D). Vertex AI can provide metrics like accuracy, ROC-AUC, precision, and recall, which are crucial for churn prediction evaluation.
Show 2 more comments
  1. guilhermebutzke 👍 1 Answered B
    My Answer: B predict customer churn, which is a binary classification problem (whether a customer will churn or not). And, the phrase "thoroughly evaluate its performance" does suggest a more comprehensive approach, and in that sense, option B could be seen as a better answer than D.
  2. BlehMaks 👍 1 Answered B
    B because Vertex AI provides us with more functions to evaluate model performance then just CONFUSION_MATRIX https://cloud.google.com/vertex-ai/docs/evaluation/introduction#classification_1

Reader comments & corrections

No reader corrections yet — spotted an error or have a note? Share it below.

Log in to comment, report an error, or add a note about this question.

How to Minimize Development Time for Weekly TensorFlow Retraining in Vertex AI?

S-grade

How to Handle Categorical Features in BigQuery ML for Fast Deployment?

S-grade

How to preprocess BigQuery data for TensorFlow?

S-grade

How to Track Model and Prediction Lineage in Vertex AI?

S-grade

Practice All PMLE Questions

Access 65 questions with complete answers and detailed explanations.

View Full PMLE Practice Test →

← Back to PMLE Study Guide