This is a dedicated watch page for a single video.
Scenario: A data scientist has developed a BigQuery ML model and requests your assistance in setting up an ML pipeline for serving predictions. Your REST API application needs to provide predictions for a single user ID with a latency of less than 100 milliseconds. The prediction query used is: SELECT predicted_label, user_id FROM ML.PREDICT (MODEL 'dataset.model', table user_features). Question: How can you establish the ML pipeline to meet the requirements of serving predictions for an individual user ID within 100 milliseconds using the given prediction query?