Skip to main content

Using model scores as predictors

4 Tasks

15 mins

Visible to: All users
Beginner Pega Customer Decision Hub 8.8 English

Scenario

U+ Bank is implementing cross-selling of its credit cards on the web by using Pega Customer Decision Hub™. To further enhance the predictive power of the adaptive models, you create a parameterized predictor that is the on-the-fly score of a predictive churn model that runs in Customer Decision Hub.

Use the following credentials to log in to the exercise system:

Role User name Password
Data Scientist DataScientist rules
Caution: This challenge requires specific artifacts. Ensure that you click Initialize (Launch) Pega instance for this challenge to get the correct exercise system.

Your assignment consists of the following tasks:

Task 1: Add a parameter to the adaptive model

In the Web_Click_Through_Rate model, create a parameterized predictor that calculates the churn risk for a customer.

Task 2: Add a sub-strategy to the NBA Framework decision strategy

In the WebTreatmentModelImpl strategy, create an external sub-strategy.

Task 3: Create a decision strategy that references a churn model

Create a decision strategy that references the ChurnH2O model, and then set the decision strategy as the external strategy in the sub-strategy component.

Task 4: Configure the adaptive model component

Configure the adaptive model component with the new parameterized predictor.

Note: If you have completed the previous challenge, Using behavioral data as predictors, you can re-use your exercise system, but some screenshots might look slightly different.

 

You must initiate your own Pega instance to complete this Challenge.

Initialization may take up to 5 minutes so please be patient.

Challenge Walkthrough

Detailed Tasks

1 Add a parameter to the adaptive model

  1. On the exercise system landing page, click Pega CRM suite to log in to Pega Customer Decision Hub™.
  2. Log in as a data scientist:
    1. In the User name field, enter DataScientist
    2. In the Password field, enter rules.
  3. In the navigation pane of Customer Decision Hub, click Intelligence > Prediction Studio to open Prediction Studio.
  4. On the Predict Web Propensity tile, click Open prediction to edit the web propensity prediction.
  5. On the Models tab of the prediction, in the Supporting models section, click Web_Click Through_Rate to open the adaptive model rule.
    This image shows the supporting models
  6. In the adaptive model rule, click the Predictors tab.
  7. On the Predictors tab, click the Parameters tab, and then click Add parameter.
  8. In the Name field, enter ChurnRisk.
  9. In the Data type list, select Double.
  10. Confirm that the predictor type is Numeric.
    The ChurnRisk parameter
  11. In the upper-right corner, click Save to save the new parameter.
  12. In the upper-left corner, click the Back icon to return to the prediction.
    This image shows theBack to the prediction button

2 Add a sub-strategy to the NBA Framework decision strategy

  1. On the Models tab, in the Supporting models section, click Web_Click Through_Rate_Customers to open the strategy.
  2. In the upper-right corner, click Check out to check out the strategy for editing.
  3. On the canvas, in the Customers area, click + > Sub strategy > External to add a sub-strategy component to the canvas.
    This image shows how to add an external Sub strategy
  4. On the canvas, connect the components as shown in the following image:
    This image shows the strategy with new sub strategy
  5. Right-click the Sub Strategy component, and then select Properties to open the External strategy properties dialog box.
  6. In the External strategy properties dialog box, in the Name field, enter Churn Risk.
  7. On the External strategy tab, click Another page to run the strategy on a defined page.
  8. In the Page field, enter Customer.
  9. Confirm that the Class field auto-populates to UBank-CDH-Data-Customer.

3 Create a decision strategy that references a churn model

  1. In the External strategy properties dialog box, in the External strategy field, enter ChurnRisk.
  2. Next to the External strategy field, click the Target icon to open the Strategy Record Configuration landing page.
    This image shows the external strategy properties dialog box
  3. On the Strategy Record Configuration landing page, in the upper-right corner, click Create and open to create the strategy.
    1. On the canvas, right-click, and then select Enable external input to add the input component to the canvas.
    2. On the canvas, right-click, and then select Decision analytics > Predictive model to add a predictive model component to the canvas.
    3. Connect the external input to the predictive model component and the predictive model component to the results, as shown in the following image:
      This image shows the external strategy
    4. Right-click the Predictive Model component, and then select Properties to open the Predictive model properties dialog box.
    5. In the Predictive model properties dialog box, in the Predictive model field, press the down arrow key, and then double-click ChurnH2O to select the model and auto-populate the Name field.
    6. Click the Output mapping tab, and then select Add item.
    7. In the Target field, enter ChurnRisk.
    8. In the Source (ChurnH2O) list, select Propensity.
    9. Next to the Target field, click the Target icon to open the Property Record Configuration landing page.
    10. On the Property Record Configuration landing page, in the upper-right corner, click Create and open to edit the property.
      1. In the Property type section, click change.
      2. In the Single Value column, select Double.
      3. In the upper-right corner, click Save.
  4. Close the ChurnRisk property.
  5. Click Submit to close the Predictive model properties dialog box.
  6. In the upper-right corner of the canvas, click Save.
  7. Close the canvas.
  8. Click Submit to close the External strategy properties dialog box.

4 Configure the adaptive model component

  1. On the canvas, right-click the Web_Click Through_Rate_Customers adaptive model component, and then select Properties to open the Adaptive model properties dialog box.
  2. In the Parameterized predictors section, in the ChurnRisk field, enter or select .ChurnRisk.
    This image shows the ChurnRisk strategy property
  3. Click Submit.
  4. In the upper-right corner, check in the strategy with appropriate comments.
  5. In the lower-left corner, click Back to Pega Prediction Studio.

Confirm your work

  1. On the exercise system landing page, click U+ Bank to launch the U+ Bank website.
    This image shows the UBank tile
  2. On the U+ Bank website, in the upper-right corner, click Log in to access the site as Troy and display the marketing banner.
  3. In the marketing banner, click Learn more to record a positive response.
  4. In the upper-right corner, click the user image, and then click Log out.
    This image shows how to log out Troy
  5. Repeat step 2 to log in as Barbara.
  6. As Barbara, repeat steps 3-4 to record a positive response, and then log out of the U+ Bank website.
    Tip: Simulating customer interactions triggers the creation of the underlying adaptive models.
  1. In Prediction Studio, in the upper-right corner, click Actions > Refresh.
  2. On the Models tab, in the Supporting models list, confirm that the ChurnH2O model is present.
  3. Click Web_Click_Through_Rate to open the adaptive model.
    This image shows the supporting models and how to go to the adaptive model
  4. On the Monitor tab, click Refresh data.
  5. On the Monitor-Predictors tab, click Predictor name to sort the list of predictors column in descending order.
  6. Confirm that the ChurnRisk parameter is listed and currently inactive in all models.

This Challenge is to practice what you learned in the following Modules:


Available in the following missions:

If you are having problems with your training, please review the Pega Academy Support FAQs.

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 Academy has detected you are using a browser which may prevent you from experiencing the site as intended. To improve your experience, please update your browser.

Close Deprecation Notice