Tutorials for Amazon Redshift ML - Amazon Redshift
Services or capabilities described in Amazon Web Services documentation might vary by Region. To see the differences applicable to the China Regions, see Getting Started with Amazon Web Services in China (PDF).

Tutorials for Amazon Redshift ML

You can use Amazon Redshift ML to train machine learning models using SQL statements, and then invoke the models in SQL queries for prediction. Machine learning in Amazon Redshift trains a model with one SQL command. Amazon Redshift automatically launches a training job in Amazon SageMaker and generates a model. Once a model is created, you can perform predictions in Amazon Redshift using the model’s prediction function.

Follow the steps in these tutorials to learn about Amazon Redshift ML features:

  • Tutorial: Building customer churn models – In this tutorial, you use Amazon Redshift ML to create a customer churn model with the CREATE MODEL command, and run prediction queries for user scenarios. Then, you implement queries using the SQL function that the CREATE MODEL command generates.

  • Tutorial: Building remote inference models – The following tutorial goes over the steps of how to create a Random Cut Forest model that has been previously trained and deployed in Amazon SageMaker, outside of Amazon Redshift.

  • Tutorial: Building K-means clustering models – In this tutorial, you use Amazon Redshift ML to create, train, and deploy a machine learning model based on the K-means algorithm.

  • Tutorial: Building multi-class classification models – In this tutorial, you use Amazon Redshift ML to create a machine learning model that solves multi-class classification problems. The multi-class classification algorithm classifies data points into one of three or more classes. Then, you implement queries using the SQL function that the CREATE MODEL command generates.

  • Tutorial: Building XGBoost models – In this tutorial, you create a model with data from Amazon S3 and run prediction queries with the model using Amazon Redshift ML. The XGBoost algorithm is an optimized implementation of the gradient boosted trees algorithm.

  • Tutorial: Building regression models – In this tutorial, you use Amazon Redshift ML to create a machine learning regression model and run prediction queries on the model. Regression models allow you to predict numerical outcomes, such as the price of a house, or how many people will use a city’s bike rental service.

  • Tutorial: Building regression models with linear learner – In this tutorial, you create a linear learner model with data from Amazon S3 and run prediction queries with the model using Amazon Redshift ML. The SageMaker linear learner algorithm solves either regression or multi-class classification problems.

  • Tutorial: Building multi-class classification models with linear learner – In this tutorial, you create a linear learner model with data from Amazon S3, and then run prediction queries with the model using Amazon Redshift ML. The SageMaker linear learner algorithm solves either regression or classification problems.