6.1.2 MySQL HeatWave AutoML Workflow

A typical MySQL HeatWave AutoML workflow is described below:

1. When you run the ML_TRAIN routine, MySQL HeatWave AutoML retrieves the data to use for training. The data can originate from either DB System tables or external Lakehouse tables. The training data is then distributed across the MySQL HeatWave Cluster, which performs machine learning computation in parallel. See Train a Model.

2. MySQL HeatWave AutoML analyzes the training data, trains an optimized machine learning model, and stores the model in a model catalog on the DB System. See Model Catalog.

3. MySQL HeatWave AutoML ML_PREDICT_* and ML_EXPLAIN_* routines use the trained model to generate predictions and explanations on test or unseen data. See Generate Predictions and Generate Explanations.

4. Predictions and explanations are returned to the DB System and to the user or application that issued the query.

Optionally, the ML_SCORE routine can be used to compute the quality of a model to ensure that predictions and explanations are reliable. See Score a Model.

To start using MySQL HeatWave AutoML with sample datasets, see Machine Learning Use Cases.

What's Next

• Learn more about the following:

  • MySQL HeatWave AutoML Learning Types

  • MySQL HeatWave AutoML Ease of Use

  • Oracle AutoML

• Learn how to Create a Machine Learning Model.