Amazon Redshift ML

Amazon Redshift ML makes it easy for data analysts and database developers to create, train, and apply machine learning models using familiar SQL commands in Amazon Redshift data warehouses. With Redshift ML, you can take advantage of Amazon SageMaker, a fully managed machine learning service, without learning new tools or languages. Simply use SQL statements to create and train Amazon SageMaker machine learning models using your Redshift data and then use these models to make predictions. For example, you can use customer retention data in Redshift to train a churn detection model and then apply that model to your dashboards for your marketing team to offer incentives to customers at risk of churning. Redshift ML makes the model available as a SQL function within your Redshift data warehouse so you can easily apply it directly in your queries and reports.

No prior ML experience needed
Because Redshift ML allows you to use standard SQL, it is easy for you to be productive with new use cases for your analytics data. Redshift ML provides simple, optimized, and secure integration between Redshift and Amazon SageMaker and enables inference within the Redshift cluster, making it easy to use predictions generated by ML-based models in queries and applications. There is no need to manage a separate inference model end point, and the training data is secured end-to-end with encryption.

Use ML on your Redshift data using standard SQL
To get started, use the CREATE MODEL SQL command in Redshift and specify training data either as a table or SELECT statement. Redshift ML then compiles and imports the trained model inside the Redshift data warehouse and prepares a SQL inference function that can be immediately used in SQL queries. Redshift ML automatically handles all the steps needed to train and deploy a model.

Predictive analytics with Amazon Redshift
With Redshift ML, you can embed predictions like fraud detection, risk scoring, and churn prediction directly in queries and reports. Use the SQL function to apply the ML model to your data in queries, reports, and dashboards. For example, you can run the “customer churn” SQL function on new customer data in your data warehouse on a regular basis to predict customers at risk of churn and feed this information to your sales and marketing teams so they can take preemptive action such as sending these customers an offer designed to retain them.

Bring your own model (BYOM)
Redshift ML supports using BYOM for local or remote inference. You can use a model trained outside of Redshift with Amazon SageMaker for in-database inference local in Amazon Redshift. You can import SageMaker Autopilot and direct Amazon SageMaker trained models for local inference. Alternatively, you can invoke remote custom ML models deployed in remote SageMaker endpoints. You can use any SageMaker ML model that accepts and returns text or CSV for remote inference.