Posted On: Dec 8, 2020
HAQM Redshift ML makes it possible for data warehouse users such as data analysts, database developers, and data scientists to create, train, and deploy machine learning (ML) models using familiar SQL commands. HAQM Redshift is the most widely used cloud data warehouse and, with HAQM Redshift ML, you can now leverage HAQM SageMaker, a fully managed machine learning service, using SQL and without moving your data or learning new skills.
With HAQM Redshift ML powered by HAQM SageMaker, you can use SQL statements to create and train machine learning models from your data in HAQM Redshift and then use these models for use cases such as churn prediction and fraud risk scoring directly in your queries and reports. HAQM Redshift ML automatically discovers and tunes the best model based on the training data using HAQM SageMaker Autopilot. SageMaker Autopilot chooses among the best regression, binary, or multi-class classification and linear models.
Alternatively, you can choose a model type such as Xtreme Gradient Boosted tree (XGBoost), a problem type like regression or classification, and preprocessors or hyperparameters. HAQM Redshift ML uses your parameters to build, train, and deploy the model in the HAQM Redshift data warehouse. You can obtain predictions from these trained models using SQL queries as if you were invoking a user defined function (UDF) and leverage all benefits of HAQM Redshift, including massively parallel processing capabilities.
HAQM Redshift ML leverages your existing cluster resources for prediction so you can avoid additional HAQM Redshift charges. There is no additional HAQM Redshift charge for creating or using a model, and prediction happens locally in your HAQM Redshift cluster, so you don’t have to pay extra unless you need to resize your cluster. HAQM Redshift ML uses HAQM SageMaker for training your model, which does have an additional associated cost. View the Redshift pricing page for details.
The Redshift ML preview is available in the following regions: US East (Ohio), US East (N Virginia), US West (Oregon), US West (San Francisco), Canada (Central), Europe (Frankfurt), Europe (Ireland), Europe(London), Europe (Paris), Europe (Stockholm), Asia Pacific (Hong Kong) Asia Pacific (Tokyo), Asia Pacific (Singapore), Asia Pacific (Sydney), and South America (São Paulo). To get started and learn more, visit the preview documentation or read this blog post.