Since Aurora makes direct calls to SageMaker and Comprehend that don’t go through the application layer, Aurora machine learning is suitable for low-latency, real-time use cases such as fraud detection, ad targeting, and product recommendations, where machine learning-based predictions need to be quickly made on large amounts of data. You can use any ML model available in SageMaker, or you can run sentiment analysis using Comprehend.
There’s no additional charge beyond the price of the AWS services that you are using. Aurora machine learning is available for Amazon Aurora with MySQL 5.7 compatibility; the SageMaker integration is generally available and the Comprehend integration is in preview. You can get started with just a few clicks by upgrading to the latest version of Aurora and giving your Aurora cluster access to SageMaker or Comprehend in the Amazon RDS Management Console. Read our blog, the Aurora ML feature page, and the Aurora documentation to learn more.
Amazon Aurora combines the performance and availability of high-end commercial databases with the simplicity and cost-effectiveness of open source databases. It provides up to five times better performance than the typical MySQL database and three times the performance of the typical PostgreSQL database, together with increased scalability, durability, and security. For more information, please visit the Amazon Aurora product page, and view the AWS Region Table for regional availability.