How to predict customer lifetime value simply in BigQuery?

You work for a company that sells corporate electronic products to thousands of businesses worldwide. Your company stores historical customer data in BigQuery. You need to build a model that predicts customer lifetime value over the next three years. You want to use the simplest approach to build the model and you want to have access to visualization tools. What should you do?

Create a Vertex AI Workbench notebook to perform exploratory data analysis. Use IPython magics to create a new BigQuery table with input features. Use the BigQuery console to run the CREATE MODEL statement. Validate the results by using the ML.EVALUATE and ML.PREDICT statements.
Run the CREATE MODEL statement from the BigQuery console to create an AutoML model. Validate the results by using the ML.EVALUATE and ML.PREDICT statements. Source Reference Answer
Create a Vertex AI Workbench notebook to perform exploratory data analysis and create input features. Save the features as a CSV file in Cloud Storage. Import the CSV file as a new BigQuery table. Use the BigQuery console to run the CREATE MODEL statement. Validate the results by using the ML.EVALUATE and ML.PREDICT statements.
Create a Vertex AI Workbench notebook to perform exploratory data analysis. Use IPython magics to create a new BigQuery table with input features, create the model, and validate the results by using the CREATE MODEL, ML.EVALUATE, and ML.PREDICT statements.

Community Votes

58%

25%

17%

58% of anonymous learners picked answer B. Votes are pick records left by other test-takers — they are not the verified answer.

Community Insight

This question tests your ability to choose the simplest ML workflow, with the trap being assuming Vertex AI Workbench is required for visualization or feature engineering when BigQuery ML handles both automatically.

To predict customer lifetime value with the simplest method, use BigQuery ML's AutoML capabilities. The community agrees that running the CREATE MODEL statement directly in BigQuery minimizes complexity while providing necessary visualization tools.

Users often select Option D because they prefer the all-in-one environment of Vertex AI Workbench, but it involves more manual coding and setup than the SQL-only approach required for the 'simplest' solution.

Community Discussion (14 comments)

pertoise 👍 6

Option B because there's no mention of "flexibility". Easy access to viz tools with Looker

NithishReddyNY 👍 1 Selected: D

Option D provides the best balance of simplicity and meeting all requirements. It allows for visualization and EDA in Vertex AI Workbench and uses the simplest modeling approach (BQML via SQL commands) executed directly from the notebook environment using IPython magics, creating a cohesive and straightforward workflow.

Wuthuong1234 👍 1 Selected: B

The correct answer is probably B. AutoML does the feature engineering for you, so it requires the least amount of effort. For all other options, you have to do the exploration and feature engineering yourself, which will take a lot of time. In a real world scenario you'd expect to do a bit of EDA to identify and deal with missing values and to check the data quality though... even if you go for the B option.

Dirtie_Sinkie 👍 2 Selected: D

Going for D

andymetzen 👍 2

Option D is the answer given by an official Google trainer.

tardigradum 👍 1

Simple training and integration with visualization tools = BQ

LaxmanTiwari 👍 2 Selected: B

As requested :" simplest approach", the option B is the best choice.

rcapj 👍 4

D Vertex AI Workbench notebook: Provides an environment for data analysis, model building, and visualization tools all in one place. IPython magics: Allows seamless interaction with BigQuery for data exploration and feature creation directly within the notebook. CREATE MODEL statement: Enables model creation within the notebook environment, simplifying the workflow. ML.EVALUATE and ML.PREDICT statements: Facilitate model validation directly within the notebook for assessing performance.

omermahgoub 👍 3

B. Use Bigquery ML Features to create, evaluate and predict

daidai75 👍 2 Selected: B

As requested :" simplest approach", the option B is the best choice.

b1a8fae 👍 1 Selected: B

Forgot to vote.

b1a8fae 👍 2

Simplest approach that allows visualization is option B.

winston9 👍 1 Selected: B

all the other options create a new BQ table, I don't think it's needed.

pikachu007 👍 2 Selected: A

Option B: While AutoML simplifies model selection and training, it lacks the flexibility and visualization capabilities of Vertex AI Workbench. Option C: Manually saving features as CSV files and importing them back into BigQuery involves unnecessary data movement and complexity. Option D: Completing all steps within the notebook is possible but requires more coding and might not be as intuitive for those less familiar with BigQuery ML syntax.

Comments & Corrections

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

Expert Analysis

Why the Answer Is Correct

Option B is correct because BigQuery ML (BQML) allows you to create and execute machine learning models directly in BigQuery using standard SQL queries. By using the CREATE MODEL statement with the AUTOML option, Google automates feature engineering, model selection, and hyperparameter tuning, satisfying the requirement for the "simplest approach." Additionally, BigQuery provides built-in visualization tools and integrates seamlessly with Looker Studio, fulfilling the visualization requirement without the need for external notebooks or complex data movement.

Why the Other Options Are Wrong

Options A and D suggest using Vertex AI Workbench and IPython magics, which introduces unnecessary complexity and coding overhead compared to a pure SQL solution. Option C involves exporting data to Cloud Storage and re-importing it, which is inefficient and contradicts the goal of simplicity. While Option D keeps the workflow within the notebook, it still requires more manual effort for data exploration and feature creation than the automated capabilities of BigQuery ML AutoML.

Community Comment Notes

The community strongly supports Option B, emphasizing that "simplest" implies minimizing manual steps and code. Several users noted that AutoML handles feature engineering automatically, which is a significant time-saver over manual exploration in a notebook. Although one comment mentioned an official trainer preferred Option D, the majority argued that the visualization requirement is met by BigQuery's native tools, making the notebook setup superfluous for this specific scenario.

Official Reference

Exam Strategy

Look for keywords like "simplest," "least effort," or "no code" to identify BigQuery ML AutoML solutions. Avoid choosing notebook solutions if the data already resides in BigQuery and visualization requirements are standard.

Related Analysis

Practice All PMLE Questions

Access 65 questions with complete answers and detailed explanations.

View Full PMLE Practice Test →

← Back to PMLE Study Guide