Using offline model scores as predictors

3 Tasks

15 mins

Pega Customer Decision Hub '23 Visible to: All users

Beginner Pega Customer Decision Hub '23 English

Scenario

U+ Bank uses Pega Customer Decision Hub™ for engagement with its customers. Externally, the data scientist team produces many product group scores for each customer, and for each channel. To make these scores available to the adaptive models as candidate predictors, a Decisioning Architect creates a database table to accommodate the data. As a Data Scientist, you add the candidate predictors to the adaptive model rule configurations as parameterized predictors, and you modify the decision strategy to select the applicable scores.

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

Role	User name	Password
Data Scientist	DataScientist	rules

Your assignment consists of the following tasks:

Task 1: Create a property to store the parameter value

In Next-Best-Action Designer, create a property to store the offline model scores.

Task 2: Add a Data Join component to the NBA Pre-Process Extension Point strategy

In the NBAPreProcessExtension strategy, add a Data join component that outputs only the relevant scores based on the action category and the web treatment.

Task 3: Configure the prediction

Configure the Predict Web Propensity prediction with the new parameterized predictor to map to OfflineProductScores.

 

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

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

• Log In

Challenge Walkthrough

Detailed Tasks

1 Create a property to store the parameter value

1. On the exercise system landing page, click Pega Infinity™ to log in to 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 Next-Best-Action > Designer.
4. In Next-Best-Action Designer, click the Taxonomy tab, and then click the Properties tab.
5. Click Edit, and then click Add property under the Properties list to create the new property.
6. In the Create property dialog box, configure the property:
   1. In the Name field, enter OfflineProductScores.
   2. In the Property type field, select Decimal.
   3. In the Property usage section, select the Dynamic radio button.
   4. Clear the Include this property in strategy results for Inbound channels checkbox.
   5. Clear the This property is persisted to storage and available for offer processing checkbox.
7. Click Submit to close the dialog box.
8. Click Save to save the Taxonomy configuration.
   Note: Saving the taxonomy may take some time as it regenerates the entire Next-Best-Action framework.

2 Add a Data Join component to the NBA Pre-Process Extension Point strategy

1. In the header of Customer Decision Hub, in the Search field, enter NBAPreProcessExtension, and then press the Enter key.
2. In the search results click NBAPreProcessExtension to open the strategy.
3. In the upper-right corner, click Save as.
4. In the Context section, in the Apply to field, select Data-Decision-Request-Customer-CDH.
5. In the Strategy Record Configuration section, define the strategy in the CDH-SR class.
6. In the upper-right corner, click Create and open to edit the strategy.
   Note: If you have used your exercise system for another challenge, steps 2-7 may not be required. Open the strategy configured on the Data-Decision-Request-Customer-CDH class.

7. On the canvas, right-click, and then select Enrichment > Data Join.
8. Connect the External Input component to the Data Join component to the Results component.
   
9. Right-click the Data Join component, and then select Properties to open the Data join properties dialog box.
10. In the Data join properties dialog box, in the Name field, enter Join product group scores.
11. In the Join source components with section, in the Type field, select Pages.
12. In the Name field, select .Customer.OfflineProductScores.
13. In the Join when all conditions below are met section, click Add item to add a condition.
14. Configure the Condition to read When .pyChannel is equal to "Web".
15. Configure a second condition to read When .Category is equal to .Category.
    
16. Ensure the Exclude source component results that do not match join condition checkbox is clear.
17. On the Properties mapping tab, in the Define mapping section, click Add item.
18. In the Target field, enter .OfflineProductScore.
19. In the Source field, enter or select .Score.
    
20. Click Submit to return to the canvas.
21. In the upper-right corner, click Check in to save your work and check in the strategy.
22. In the Check-in comments field, enter appropriate comments, and then click Check in.

3 Configure the prediction

1. In the navigation pane of Customer Decision Hub, click Intelligence > Prediction Studio to open Prediction Studio.
2. On the Predict Web Propensity tile, click Open prediction.
3. On the Settings tab, in the Prediction details section, click Configure.
4. In the Prediction properties window, in the Save results to section, select the CDH-SR radio button.
5. Click Submit to close the dialog box.
6. Confirm that you are aware that any previous learning will no longer be available, and then click Yes.
7. On the Models tab, in the Web Click Through Rate Customer row, click 6 Parameters to edit the parameters.
8. In the Edit Parameters dialog box, click Add parameterized predictor.
9. In the Name field of the new parameter, enter OfflineProductScores.
10. In the Data type list, select Decimal.
11. In the upper-right corner of the dialog box, click the Next page icon.
12. Confirm that the Predictor type of the new parameter is Numeric.
13. Click inside the Field field, and enter or select .OfflineProductScores.
14. Click Submit to close the dialog box.
15. In the upper-right corner, click Save.

Confirm your work

1. Click Web Click Through Rate Customer to open the adaptive model.
2. On the Predictors > Parameters tab, confirm that the new parameterized predictor is listed.
   
   Note: When you click, in the upper-right corner, Submit prediction for deployment, all changes to the prediction are included in a branch that need to be merged by a System Architect before they take effect.

---

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

• Defining prediction patterns v2

---

Available in the following mission:

• AI for 1:1 Customer Engagement v3