Training the matrix factorization model

In this section, we'll train the BigQuery ML matrix factorization model in order to build a recommendation system with the e-commerce data that we've already prepared.

Let's start training the purchase_recommender ML model by executing the following SQL statement:

CREATE OR REPLACE MODEL `09_recommendation_engine.purchase_recommender`
OPTIONS(model_type='matrix_factorization',
        user_col='fullVisitorID',
        item_col='purchased_product_id',
        rating_col='quantity',
        feedback_type='implicit'
        )
AS
SELECT fullVisitorID, purchased_product_id, quantity 
FROM `09_recommendation_engine.product_purchases`; 

The first few lines of the query are composed...