ASSOCIATE-DATA-PRACTITIONER practice question 25 of 25

You work for an ecommerce company that has a BigQuery dataset that contains customer purchase history, demographics, and website interactions. You need to build a machine learning (ML) model to predict which customers are most likely to make a purchase in the next month. You have limited engineering resources and need to minimize the ML expertise required for the solution. What should you do?

Full set: 106 questions
Answer options
A: Use BigQuery ML to create a logistic regression model for purchase prediction. Correct answer
B: Use Vertex AI Workbench to develop a custom model for purchase prediction.
C: Use Colab Enterprise to develop a custom model for purchase prediction.
D: Export the data to Cloud Storage, and use AutoML Tables to build a classification model for purchase prediction.
Correct Answer:
A. Use BigQuery ML to create a logistic regression model for purchase prediction.
Explanation

BigQuery ML is designed specifically for this scenario. It enables users to build and train machine learning models, including logistic regression for classification tasks, directly on data within BigQuery using standard SQL syntax. This approach minimizes data movement and leverages existing SQL skills, perfectly aligning with the requirements to use limited engineering resources and minimize the need for specialized ML expertise. The entire workflow from data preparation to prediction can be managed within BigQuery.

Why Incorrect

B. Vertex AI Workbench is a notebook-based environment for data scientists and requires significant coding and ML expertise, which contradicts the user's constraints.
C. Colab Enterprise is also a notebook-based environment requiring custom code and ML expertise, making it unsuitable for a team with limited resources in this area.
D. While AutoML Tables is a low-code solution, this option requires an unnecessary data export step from BigQuery to Cloud Storage, adding complexity and engineering overhead.

References

1. Google Cloud Documentation, "Introduction to BigQuery ML". It states, "BigQuery ML lets you create and execute machine learning models in BigQuery by using standard SQL queries. BigQuery ML democratizes machine learning by letting SQL practitioners build models using their existing tools and skills."

2. Google Cloud Documentation, "The CREATE MODEL statement for logistic regression models". This page provides the exact SQL syntax for creating a logistic regression model, demonstrating the simplicity and SQL-native approach of BigQuery ML for this type of prediction task.

Scroll to Top