MySQL HeatWave customers now have access to MySQL HeatWave AutoML, which is a fully managed, highly scalable, cost-efficient, machine learning solution for data stored in MySQL. MySQL HeatWave AutoML provides a simple SQL interface for training and using predictive machine learning models, which can be used by novice and experienced ML practitioners alike. With MySQL HeatWave AutoML, you can train a model with a single call to an SQL routine. Similarly, you can generate predictions with a single CALL or SELECT statement which can be easily integrated with your applications.

With MySQL HeatWave AutoML, data and models never leave the MySQL Database Service, saving you time and effort while keeping your data and models secure. MySQL HeatWave AutoML is optimized for MySQL HeatWave shapes and scaling, and all MySQL HeatWave AutoML processing is performed on the MySQL HeatWave Cluster. ML computation is distributed among MySQL HeatWave nodes, taking advantage of MySQL HeatWave's scalability and massively parallel processing capabilities. For more information about MySQL HeatWave's machine learning capabilities, see Train and Use Machine Learning Models. (WL #14661, WL #14836, WL #15014)

MySQL HeatWave now compresses data as it is loaded, which permits MySQL HeatWave nodes to store more data. More data per node reduces costs by minimizing the size of the MySQL HeatWave Cluster required to store your data. Data compression is enabled by default but can be disabled at runtime using the rapid_compression session variable. For more information, see Enable or Disable Data Compression. (WL #14868)