Google Cloud Professional Machine Learning Engineer — Question 269

You work at a gaming startup that has several terabytes of structured data in Cloud Storage. This data includes gameplay time data, user metadata, and game metadata. You want to build a model that recommends new games to users that requires the least amount of coding. What should you do?

Answer options

• A. Load the data in BigQuery. Use BigQuery ML to train an Autoencoder model.
• B. Load the data in BigQuery. Use BigQuery ML to train a matrix factorization model.
• C. Read data to a Vertex AI Workbench notebook. Use TensorFlow to train a two-tower model.
• D. Read data to a Vertex AI Workbench notebook. Use TensorFlow to train a matrix factorization model.

Correct answer: B

Explanation

The best approach is to use BigQuery ML to train a matrix factorization model, as it is specifically designed for recommendation systems and requires minimal coding. Option A is incorrect because an Autoencoder is not the ideal choice for recommendations. Options C and D involve TensorFlow, which typically requires more coding and setup than using BigQuery ML.