Skip to main content


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

This content has been archived and is no longer being updated.

Links may not function; however, this content may be relevant to outdated versions of the product.

Initializing predictive model monitoring

Updated on March 11, 2021

Verify that DMSample predictive models accurately predict customer behavior by generating sample reports. To generate sample reports, simulate historical customer responses to model predictions by running the InitializePMMonitoring activity.

Predictive models use data mining and probability to forecast outcomes, such as the likelihood to accept an offer or churn. Each model is made up of a number of predictors, which are variables that are likely to influence future results.
Before you begin: Generate DMSample data. For more information, see Initializing DMSample data.
  1. Open the InitializePMMonitoring activity rule:
    1. In the navigation pane of Dev Studio, click Records.
    2. Expand the Technical category and click Activity.
    3. In the Activity Name column, click the Filter icon.
    4. In the Search Text field, enter InitializePMMonitoring, and then click Apply.
    5. In the Activity Name column, click InitializePMMonitoring.
  2. On the Activity: InitializePMMonitoring tab, click ActionsRun.
  3. In the Run Activity: InitializePMMonitoring window, in the noOfDaysToSimulate field, enter the number of days for which you want to simulate responses to predictive models.
    Note: The recommended number of days is 4. Depending on your system resources, you can increase this value. However, the reports might take significantly longer to generate.
  4. Click Run.
  5. Verify that the model reports are populated with data:
    1. In the navigation pane of Dev Studio, click Records.
    2. Expand the Decision category, and then click Predictive Model.
    3. Click any model from the list, for example, PredictChurn.
    4. Click the Monitor tab.
    5. If no data is displayed, click Refresh data.
    6. Review the performance and analytical reports for the model that you selected.
    The following figure shows the number of reports that were generated for a churn prediction model over a period of four days:
    Reports for the Predict Churn predictive model
    Predictive Model: Predict Churn; Monitor tab; Time range: All time; Performance (AUC) 60.46; Total responses 1,154; Score distribution; Success rate 6.37%
Result: You have fully configured the DMSample data and you are ready to discover the next-best-action features on Pega Platform.

    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