Which Google Cloud service or feature lets you build machine learning (Digital Leader)

Correct answer: A) BigQuery ML.
Google Cloud BigQuery ML is a powerful tool that allows users to create and execute machine learning models directly within BigQuery using SQL queries. This service is designed to democratize machine learning by enabling SQL practitioners to build models using their existing tools, thereby eliminating the need for data movement. This means that users can leverage their SQL skills to create, train, evaluate, and predict with machine learning models without having to move data out of BigQuery.

BigQuery ML supports a variety of machine learning tasks, including binary logistic regression, which is used to predict whether a website visitor will make a transaction, as demonstrated in the tutorial using the Google Analytics sample dataset. The service automatically splits input data into a training set and a holdout set to avoid overfitting the model, ensuring that the model generalizes well to unseen data.

To create a machine learning model in BigQuery ML, users can use the CREATE MODEL statement, specifying the type of model and the features to be used. Once the model is created, it can be evaluated using the ML.EVALUATE function and predictions can be made using the ML.PREDICT function. This process allows for a seamless integration of machine learning capabilities directly within the SQL environment, making it accessible to a wide range of users, including those with SQL expertise but limited machine learning experience.

BigQuery ML is part of the broader Google Cloud ecosystem, offering a comprehensive suite of tools for data analysis and machine learning. It integrates seamlessly with other Google Cloud services, providing a unified platform for data storage, analysis, and machine learning model development and deployment.