You're reading from Machine Learning with BigQuery ML Create, execute, and improve machine learning models in BigQuery using standard SQL queries

Product type Paperback

Published in Jun 2021

Publisher Packt

ISBN-13 9781800560307

Length 344 pages

Edition 1st Edition

Languages

Python

Tools

BigQuery

Concepts

Machine Learning

Author (1):

Alessandro Marrandino

View More author details

Table of Contents (20) Chapters

Preface

1. Section 1: Introduction and Environment Setup

2. Chapter 1: Introduction to Google Cloud and BigQuery FREE CHAPTER

3. Chapter 2: Setting Up Your GCP and BigQuery Environment

4. Chapter 3: Introducing BigQuery Syntax

5. Section 2: Deep Learning Networks

6. Chapter 4: Predicting Numerical Values with Linear Regression

7. Chapter 5: Predicting Boolean Values Using Binary Logistic Regression

8. Chapter 6: Classifying Trees with Multiclass Logistic Regression

9. Section 3: Advanced Models with BigQuery ML

10. Chapter 7: Clustering Using the K-Means Algorithm

11. Chapter 8: Forecasting Using Time Series

12. Chapter 9: Suggesting the Right Product by Using Matrix Factorization

13. Chapter 10: Predicting Boolean Values Using XGBoost

14. Chapter 11: Implementing Deep Neural Networks

15. Section 4: Further Extending Your ML Capabilities with GCP

16. Chapter 12: Using BigQuery ML with AI Notebooks

17. Chapter 13: Running TensorFlow Models with BigQuery ML

18. Chapter 14: BigQuery ML Tips and Best Practices

19. Other Books You May Enjoy

Using the matrix factorization model

In this section, we'll test the matrix factorization model to get the recommended products for the users of our website.

To use our BigQuery ML model, we'll use the ML.RECOMMEND function while specifying the parameters for our prediction.

The recommendation engine does not need to take any additional input parameters besides the model itself. If the model has one input column, the model will only return the recommendations for the rows in the input. If no input values are provided, the model will apply the prediction for each combination of users and items in the original dataset.

ML.RECOMMEND returns three columns:

A column that represents the user. In our implementation, this is identified by the fullVisitorID column.
A field dedicated to the item that is recommended to a specific user. In our case, this is represented by the purchased_product_id column.
A third column that represents the predicted rating...