Scribd
Upload
204 views2 pages

BigQuery ML Documentation

BigQuery ML allows users to build machine learning models on data stored in BigQuery without needing to copy or reformat the data, improving efficiency. It uses SQL commands, meaning users can leverage a familiar language to create their own models. Supported model types include linear regression for numerical prediction, binary and multiclass logistic regression for classification into two or multiple classes.

Uploaded by

Thursy Satriani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
204 views2 pages

BigQuery ML Documentation

BigQuery ML allows users to build machine learning models on data stored in BigQuery without needing to copy or reformat the data, improving efficiency. It uses SQL commands, meaning users can leverage a familiar language to create their own models. Supported model types include linear regression for numerical prediction, binary and multiclass logistic regression for classification into two or multiple classes.

Uploaded by

Thursy Satriani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

BigQuery ML 

 
 

 
There are two key benefits of BigQuery ML. First, it works on your data that is already in BigQuery 
storage -- in your Data Warehouse or Data Lake. 
So the data does not need to be copied out of BigQuery or reformatted. This improves efficiency in 
many ways, and in some cases resolves privacy concerns. 
 
Second, BigQuery ML uses SQL commands. That means BigQuery users can learn to create their own 
models by extending their use of a language they already know. 
 
Works with full models (not Custom Models like Cloud AutoML). 
 
The locality of your model is the same as your dataset. So that is defined when the dataset is created. 
 
 
 
Linear regression models predict a numerical value. Binary logistic regression models identify one of 
two classes. Multiclass logistic regression models are used for classification. 
You can read about currently supported models in the online documentation. 
 
https://pixabay.com/vectors/banana-fruit-yellow-fresh-healthy-310449/ 
 
 
 
 
 

You might also like