How to forecast sales with minimal effort in BigQuery?

You work for an online retailer. Your company has a few thousand short lifecycle products. Your company has five years of sales data stored in BigQuery. You have been asked to build a model that will make monthly sales predictions for each product. You want to use a solution that can be implemented quickly with minimal effort. What should you do?

  1. Use Prophet on Vertex AI Training to build a custom model.
  2. Use Vertex AI Forecast to build a NN-based model.
  3. Use BigQuery ML to build a statistical ARIMA_PLUS model. Source Reference Answer
  4. Use TensorFlow on Vertex AI Training to build a custom model.

Community Votes

C
100%

100% of anonymous learners picked answer C. Votes are pick records left by other test-takers — they are not the verified answer.

Community Insight

This question tests the ability to identify the lowest-friction path for ML by using native database tools, avoiding the trap of over-engineering with Vertex AI when data is already in BigQuery.

BigQuery ML ARIMA_PLUS is the optimal solution for quick time series forecasting when data resides in BigQuery, requiring minimal code and no data movement. The community consensus confirms that this approach offers the fastest implementation compared to custom model training.

Selecting Vertex AI Forecast is a common error because it involves unnecessary complexity and setup compared to running a simple SQL query in BigQuery ML.

Community Discussion (4 comments)

fitri001 👍 2 Selected: C
Quick Implementation: BigQuery ML simplifies the process. You can train and deploy the model directly within BigQuery, eliminating the need for complex model deployment or data movement. Minimal Effort: ARIMA_PLUS is a pre-built statistical model available in BigQuery ML. You don't need to write custom code for a complex neural network (NN) model like in option B or D. Time Series Data: ARIMA models are well-suited for time series forecasting, which is ideal for your monthly sales prediction task.
pinimichele01 👍 1 Selected: C
data on bigquery + minimal effort -> C
b1a8fae 👍 1 Selected: C
Given amount of data (few thousand short-cycled products) and frequency of predictions (monthly) C is the way to go.
pikachu007 👍 4 Selected: C
Ease of Use: BigQuery ML integrates seamlessly with BigQuery, allowing you to create and train models directly within SQL queries, eliminating the need for separate environments or coding. Statistical ARIMA_PLUS Strengths: This model is well-suited for time series forecasting, automatically handling seasonality, trends, and holidays, making it appropriate for monthly sales predictions. Minimal Effort: BigQuery ML handles model training and tuning, reducing the need for manual configuration or hyperparameter tuning. Fast Implementation: Model creation and training can be done in a few lines of SQL, enabling rapid deployment.

Comments & Corrections

No comments 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.

Submitted for moderation before publishing. Keep it helpful and respectful.

Expert Analysis

Why the Answer Is Correct

Option C is the correct choice because the sales data is already stored in BigQuery, and the requirement emphasizes quick implementation with minimal effort. BigQuery ML allows data scientists to build models using standard SQL queries directly within the database, eliminating the need for data extraction or complex environment setup. The ARIMA_PLUS model is specifically designed for time series forecasting, automatically handling seasonality and trends, which makes it ideal for monthly sales predictions.

Why the Other Options Are Wrong

Options A and D involve Vertex AI Training, which requires writing custom code (Python) and managing training jobs, contradicting the "minimal effort" constraint. Option B, Vertex AI Forecast, while a managed service, typically requires more configuration and potentially higher costs for a straightforward forecasting task than a native BigQuery SQL command. Additionally, moving data or setting up pipelines for Vertex AI adds latency and operational overhead compared to running the model where the data lives.

Community Comment Notes

Community feedback strongly supports Option C, noting that the combination of "data on bigquery" and "minimal effort" makes BigQuery ML the obvious winner. Users highlighted that ARIMA_PLUS is a pre-built statistical model that simplifies the process, removing the need to write complex code for neural networks. Several comments emphasized the seamless integration and speed of BigQuery ML for this specific use case.

Official Reference

https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-create-time-series

Exam Strategy

When the exam asks for "minimal effort" or "quickest implementation" and mentions BigQuery, always prioritize BigQuery ML over Vertex AI to avoid data movement and complex coding.

Related Analysis

You work for an auto insurance company. You are preparing a

S-Grade

You work for a retail company. You have a managed tabular da

S-Grade

You are building a MLOps platform to automate your company’s

A-Grade

Practice All PMLE Questions

Access 65 questions with complete answers and detailed explanations.

View Full PMLE Practice Test →

← Back to PMLE Study Guide