ML model management
You can configure and run predictions on datasets from ML Model Management.
Open an ML deployment from Catalog to go to ML Model Management. There are navigation options in the user interface for deployment information, dataset predictions, and real-time predictions.
Click View ML experiment in the bottom left corner of the page to open the ML experiment from which the ML deployment was created.
Deployment overview
The Deployment overview shows the features used in the model training and details for the deployment.
Overview of the ML deployment
Dataset predictions
Dataset predictions displays an overview of the prediction configurations of the ML deployment. You can have several prediction configurations for an ML deployment.
You can use the Actions menu to run, edit, or delete predictions. You can also edit and delete prediction schedules from this menu.
If no schedule is currently configured for your prediction, you can also use the Actions menu to create a new prediction schedule.
Dataset predictions with an overview and Actions menu expanded
If you select Edit prediction configuration, the Prediction configuration pane is opened.
Dataset predictions with side pane for prediction configuration
Real-time predictions
The Real-time predictions pane in ML model management gives you access to the real-time prediction API. For information about the prediction API, see Creating real-time predictions.
Real-time predictions pane
