After you build and solve your model in your Decision
Optimization
experiment, you are then ready to deploy the model.
You can save both model and data in a scenario for deployment. The data types set in the Prepare data
view and, if you set any run configuration
parameters for that scenario, these parameters are also saved in the deployment.
Procedure
To save your model for deployment:
-
In the Decision
Optimization
experiment UI, either from the Scenario or from the Overview pane, click the menu icon for the scenario that you want to deploy, and select Save for
deployment
- Specify a name for your model and add a description, if needed, then click
Next.
- Review the Input and Output schema and
select the tables that you want to include in the schema.
- Review the Run parameters and add, modify, or delete any
parameters as necessary.
- Review the Environment and Model files
that are listed in the Review and save window.
Any environment
that you specified to run your model with is shown in this window. This environment is then used
when you deploy your model in Watson Machine Learning (both when
you save your model for deployment and when you promote it to your deployment
space).
- Click Save.
Results
The model is then available in the Models section of your project,
from where you can promote it to a deployment space.