Official Google Cloud Certified Professional Machine Learning Engineer Study Guide

Chapter 14BigQuery ML

GOOGLE CLOUD PROFESSIONAL MACHINE LEARNING ENGINEER EXAM OBJECTIVES COVERED IN THIS CHAPTER:

• 1.1 Developing ML models by using BigQuery ML. Considerations include:
  • Building the appropriate BigQuery ML model (e.g., linear and binary classification, regression, time‐series, matrix factorization, boosted trees, autoencoders) based on the business problem
  • Feature engineering or selection by using BigQuery ML
  • Generating predictions by using BigQuery ML

BigQuery is the flagship data warehouse product in Google Cloud. It is a fully managed serverless service that can work with petabytes of data. BigQuery was released (generally available) in November 2011. Over 10 years, the popular service has grown significantly in user base as well as number of features.

You might have noticed that BigQuery ML was mentioned in many of the previous chapters. Although the current exam guide (as of writing this book) does not have a separate section for it, this is one of the most important topics for the ML certification.

In BigQuery, data is analyzed using SQL, including creating and training models. We will explain usage of BigQuery using an example. Suppose we have a dataset that has data about credit card customers and the objective is to find if a customer defaulted on their credit card payment.

BigQuery ML revolutionized the industry because it was a radical ...