Deploying a Decision Optimization model using the user interface

You can save a model for deployment in the Decision Optimization model builder and promote it to your Watson Machine Learning deployment space.

Before you begin

You must have a deployment space associated with your project.

About this task

Once you're satisfied with its results, reliability, and performance, you can deploy a model inside Decision Optimization model builder using Watson Machine Learning.

There are three main stages for deployment:
  1. From the Decision Optimization model builder, save your model scenario as a Watson Machine Learning model in your Project.
  2. Promote your Watson Machine Learning model to your deployment space.
  3. From your deployment space create a new deployment.
  4. You can then create and run jobs to your deployed model.
This is detailed in the following procedures.

Procedure

  1. In the Decision Optimization model builder, either from the Scenario or from the Overview pane, click the menu icon Scenario menu icon beside the scenario that you want to deploy, and select Save for deployment
  2. Specify a name for your model and add a description if required, then click Save.
    The model is available in the Models section of your project as a Watson Machine Learning model.
  3. View your saved Watson Machine Learning model in your project.
    You can see a summary with input and output schema. Click Promote to deployment space.
  4. In the Promote to space window that opens, check that the Target field displays the name of your deployment space and click Promote.
  5. Click the link deployment space in the message you receive that confirms successful promotion.
    Your promoted model is displayed in your Deployment space. The information panel shows you the Type, Model ID and Software specification.
  6. Open your model from the Assets tab of your deployment space and click Create a deployment.
  7. Specify a name for your deployment and select a Hardware definition.
    Click Create to create the deployment. Your deployment window opens from which you can later create jobs.

Results

You can access information about your deployment on the Deployments tab of your model in your deployment space.

Creating and running jobs

Procedure

  1. Return to your deployment space and click the data icon to open the data pane. Upload your input data tables, and solution and kpi output tables here. (You must have output tables to be able to see the solution and kpi values.)
  2. Open your deployment model, for example by selecting it in the Deployments tab of your deployment space and click Create job.
  3. Define the details of your job by entering a name, and an optional description for your job and click Next.
  4. Configure your job by selecting a hardware definition and Next.
    You can choose to schedule you job here, or just leave the default schedule option off and click Next.
  5. Choose the data you want to use in your job by clicking Select the source for each of your input and output tables. Click Next.
  6. You can now review and create your model by clicking Create.
    When you receive a successful job creation message you can then view it by opening it from your deployment space. There you can see the Run status of your job.
  7. Open the Run for your job.
    Your job log opens and you can also view and copy the payload information.

Results

You can create and monitor jobs, and get solutions using the Watson Machine Learning Python Client. See the RunDeployedModel notebook in the DO-samples on the Decision Optimization GitHub.