0 / 0
Promoting SPSS Modeler flows and models
Last updated: Feb 12, 2025
Promoting and running SPSS Modeler models and flows in watsonx.ai Runtime

You can promote SPSS Modeler flows and models to watsonx.ai Runtime if you have the watsonx.ai Runtime service.

After you build a model, you need to publish it or the flow that it is in so that others can access the model. Users, developers, or systems can access the model in the deployment space and use it to analyze data or make predictions.

In watsonx.ai Runtime, you add your flows and models to a deployment space, where you can test and manage them. In a deployment space, you can prepare your flows and models for use in pre-production or production environments to generate predictions and insights.

Deploying models and flows has these benefits.

Real-time Insights
Deployed models can provide real-time predictions or insights. Real-time data enables faster decision-making and more efficient operations.
Scalability
Deployed models can scale to handle increasing amounts of data and demand so that they maintain their performance as your business grows.
Integration
Deployed models can be integrated with other systems and applications. For example, you can use API end points to enable integration.
Security
Deployed models can be secured by using access controls, encryption, and other best practices. Security measures ensure that sensitive data remains protected.
Maintainability
Deployed models can be updated and maintained. You can update models as needed so that they remain accurate and relevant over time.

Models in deployment spaces

Models can be saved as either a scoring branch or as predictive model markup language (PMML). PMML is an XML format for describing data mining and statistical models. It includes inputs to the models, transformations that are used to prepare data for data mining, and the parameters that define the models themselves. If you save models as PMML, it is possible to share models with other applications that support this format. For more information about PMML, see the Data Mining Group website.

Models can be deployed in either online or batch deployments. For more information about deployments, see Creating online deployments and Creating batch deployments.

Flows in deployment spaces

Flows can be deployed only in batch deployments. For flows in a deployment space, you can decide which terminal nodes to run in the flow each time that you create a batch job from the flow. You can use this flexibility to run the whole flow or only a few nodes from it. You do not need to deploy the flow in the deployment space to create batch jobs.

For more information about creating batch jobs for flows in deployment spaces, see Creating jobs in deployment spaces for SPSS Modeler flows.

Promoting SPSS Modeler models and flows to watsonx.ai Runtime

You can promote any model or flow to a deployment space if it is saved as a project asset.

  1. If you want to promote a model, you need to save it to the project before you can promote it:
    1. In your SPSS Modeler flow, click the Save Model icon on the toolbar.
    2. In Branch terminal node, select the node that you want to make into a model.
    3. Enter a name and click Save to save the model to as a project asset.
  2. Promote the flow or model:
    1. Click the Assets tab and find the model or flow. Click the overflow menu and select Promote to space.
    2. In Target space, select the deployment space. Click Promote.
  3. If the flow or model needs any data assets or connections to run in the deployment space, promote them from the Assets tab as well.

In the deployment space, you can then create deployments and jobs to generate predictions for new data. For more information, see Deploying AI assets.

For a list of which data sources are supported for models in watsonx.ai Runtime, refer to the SPSS section under Batch deployment input details for SPSS Modeler models.

Importing SPSS Modeler models and flows into watsonx.ai Runtime

If you want to deploy several models and flows to a deployment space, you can export the project that they are in and then import the project in the deployment space. For more information about exporting and importing projects, see Exporting project assets and Importing space and project assets into deployment spaces.