Initializing predictive model monitoring
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.- Open the InitializePMMonitoring activity rule:
- In the navigation pane of Dev Studio, click Records.
- Expand the Technical category, and then click Activity.
- In the Activity Name column, click the Filter icon.
- In the Search Text field, enter InitializePMMonitoring, and then click Apply.
- In the Activity Name column, click InitializePMMonitoring.
- On the Activity: InitializePMMonitoring tab, click .
- 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.
- Click Run.
- Verify that the model reports are populated with data:
- In the navigation pane of Dev Studio, click Records.
- Expand the Decision category, and then click Predictive Model.
- Click any model from the list, for example, PredictChurn.
- Click the Monitor tab.
- If no data is displayed, click Refresh data.
- 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
Previous topic Initializing DMSample data Next topic Enabling decision management services