Distribute Prediction Definitions and Models with Managed and Unmanaged Packages

Build and train models using your own data, then distribute them to others—within or outside your company—using managed or unmanaged packages. Others can enjoy the benefits of your models’ predictions and improvements without needing the data to train the models themselves. Einstein Discovery supports both first-generation packaging (1GP) and second-generation packaging (2GP).

1. In Package Manager, create a package.
2. In the Components tab, click Add.
3. In the Component Type list, select Analytics Model or Analytics Model Configuration or Analytics Model Prediction Definition.
   

   Component	Description
   Analytics Model	The Einstein Discovery model, or the custom equation based on statistical understanding of past outcomes to predict future outcomes.
   Analytics Model Configuration	The metadata for the Einstein Discovery model. Use for editing or retraining the model in the target environment after migration.
   Analytics Model Prediction Definition	The parent resource of a model (or group of models) in Einstein Discovery. Use to consume model predictions and manage jobs.

4. In the list of results, select one or more models or prediction definitions.
5. Click Add Component