Skip to main content


         This documentation site is for previous versions. Visit our new documentation site for current releases.      
 

Enabling Machine Learning Operations

Updated on July 5, 2022

Enable Machine Learning Operations (MLOps) so that you can replace active models in predictions with other models, scorecards, or fields, and then deploy the candidate models to production. To enable MLOps, update Prediction Studio settings with the work queue for data scientists, email account for sending notifications, and analytics repository.

  1. In the navigation pane of Prediction Studio, click SettingsPrediction Studio settings.
  2. Optional: If you want to use a different work queue for data scientists than the default DataScientistWorkqueue, in the Work queue field, enter the name of your work queue.
  3. Optional: If you want to enable email notifications:
    1. In the Email account field, enter an email address for notifying users about the model update process.
      Tip: If you do not want to trigger any email notifications, leave this field blank.
    2. Configure the data scientist's operator ID with the same notification email address.
    3. Add the data scientist's operator ID to the work group that is configured in the model update work queue.
      Tip: For example, the default work queue DataScientistWorkqueue is configured with the Default work group. To receive emails, the operator must be a part of the Default work group.
  4. In the Storage section, in the Analytics repository, enter the name of the analytics repository for storing machine learning models.
  • Previous topic Analyzing example projects and models in Prediction Studio
  • Next topic Clearing deleted models in Prediction Studio

Have a question? Get answers now.

Visit the Support Center to ask questions, engage in discussions, share ideas, and help others.

Did you find this content helpful?

Want to help us improve this content?

We'd prefer it if you saw us at our best.

Pega.com is not optimized for Internet Explorer. For the optimal experience, please use:

Close Deprecation Notice
Contact us