Adding clickstream data to a customer profile

6 Tasks

30 mins

Pega Customer Decision Hub '24.2

Pega Customer Decision Hub '24.1 Pega Customer Decision Hub '23 Pega Customer Decision Hub 8.8 Pega Customer Decision Hub 8.7

Visible to: All users

Intermediate

Pega Customer Decision Hub '24.2

Decision Management

Next Best Action

English

Scenario

U+ Bank uses Pega Customer Decision Hub™ to present personalized credit card offers to its customers on its website. The data scientists want to leverage customers' web activity data to empower their existing AI models. As a system architect, you want to install the Behavioral Data accelerator component, extend the customer profile with financial services clickstream summary, and test the clickstream service shipped with the component. Then, as a data scientist, you want to use the financial services clickstream summary attributes as new predictors in the AI Models.

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

Role	User name	Password
System architect	SystemArchitect	rules
Data scientist	DataScientist	rules

Your assignment consists of the following tasks:

Task 1: Download the Behavioral Data accelerator component

Download the Behavioral Data accelerator component.

Task 2: Set up the Behavioral Data accelerator component

As a system architect, add the accelerator component to the implementation application.

Task 3: Associate the financial clickstream summary with the customer context

From Customer Decision Hub, add the Financial clickstream summary to the allow list and build the association with the customer context by using Customer Profile Designer.

Task 4: Test the Clickstream service

Manually invoke the Clickstream service from Dev Studio by using the following sample JSON payload and validate that your configuration is successful.

{

"CustomerID":"14",

"InterestedIn":"",

"InterestLevel":"",

"EventType":"PageView",

"PageType":"Card",

"DeviceType":"Web",

"PageViewActiveTime":"",

"CookieID":""

}

Task 5: Generate clickstream activity from U+ Bank

The U+ Bank website is configured to call the Clickstream service that you set up in previous tasks. Login to the U+ Bank website as Troy and navigate to the Credit Cards page to generate clickstream data in Customer Decision Hub. Review the generated data.

Task 6: Add financial clickstream summary predictors to AI models

As a data scientist, introduce behavioral data predictors to AI models by using the newly associated financial clickstream summary attributes.

 

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 Download the Behavioral Data accelerator component

1. Download the Behavioral Data accelerator component.

2 Set up the Behavioral Data accelerator component

1. On the exercise system landing page, click Launch Pega InfinityTM to log in to Dev Studio.
2. Log in as the system architect:
   1. In the User name field, enter SystemArchitect.
   2. In the Password field, enter rules.
3. Import the downloaded Behavioral Data accelerator component ZIP file:
   1. In Dev Studio, click Configure > Application > Distribution > Import.
   2. In the Import Wizard, click Choose File, and select the downloaded zip file to upload the component.
   3. Click Next until import is initiated and wait for the wizard to complete the import process.
   4. Once the import is complete, click Done to close the import wizard.
4. In the header of Dev Studio, click Application > Definition to open the application rule.
   
5. In the Enabled components section of the application rule, click Manage components to open the Available components window.
   
6. In the Available components window, ensure the Enabled check box is selected, click OK to dismiss the Available components window.
   
7. In the Application Definition, ensure the Behavioral data accelerator component is added to the enabled components.
8. In the upper-right corner, click Save to save the application rule.

3 Associate the financial clickstream summary with the customer context

1. In the header of Dev Studio, click Launch portal > Customer Decision Hub.
   
2. In the navigation pane of Customer Decision Hub, click Data > Profile Data Sources.
   
3. In the Profile Data Sources page, click Add and select Data flows.
4. In the Add data flow wizard, select the Process clickstream data, then click Add.
   
5. On the Summaries tab of Profile Data Sources, click the Financial services clickstream profile data source.
   
   Tip: Refresh the Summaries tab if the clickstream summaries are not available.

6. On the Summary: Financial services clickstream rule form, click Save so that Customer Decision Hub automatically generates underlying artifacts in the background (summary attributes, output class structures, dataflows).
   
   Caution: This process can take up to one minute.

7. On the Summary: Financial services clickstream page, click the Records tab to confirm that there are no records.
   
8. In the navigation pane of Customer Decision Hub, click Data > Profile Designer.
   
9. In the upper-right corner, click Edit.
10. Click Add associated data > Summary > Financial services clickstream to display the Add associated data dialog box.
    
11. In the Add associated data dialog box, click Add to add the data to the customer profile.
    
12. In the upper-right corner, click Save.
13. In the upper-right corner, click user icon, and then Log off.

4 Test the Clickstream service

1. Log in as the system architect:
   1. In the User name field, enter SystemArchitect.
   2. In the Password field, enter rules.
2. In the header of Dev Studio, search for BehavioralData and then find the Service REST rule.
3. Click the BehavioralData Service REST to open the rule properties.
   
4. In the upper-right corner, click Actions > Run.
   
5. In the Run window, configure the following settings:
   1. In the HTTP Method section, click POST.
   2. In the Message Buffer section, enter the following JSON payload:
      {
      "CustomerID":"14",
      "InterestedIn":"",
      "InterestLevel":"",
      "EventType":"PageView",
      "PageType":"Card",
      "DeviceType":"Web",
      "PageViewActiveTime":"",
      "CookieID":""
      }
      
   3. Click Execute.
6. Confirm that you received a success response from the service with HTTP Status code 200.
   
7. In your browser, close the response tab.
8. In the header of Dev Studio, click Launch portal > Customer Decision Hub to open Customer Decision Hub.
9. In the navigation pane of Customer Decision Hub, click Data > Profile Designer.
10. On the Profile Designer page, click the Financial services clickstream profile data source.
11. At the top of the summary rule, click the Records tab to review the generated records.
    
12. Scroll to the right to confirm that the CardPageVisit attributes have values.
    

5 Generate clickstream activity from U+ Bank

1. On the exercise landing page, in the upper-left corner, click App-Switcher > U+ Bank to open U+Bank website.
   
2. In the upper-right corner, click Log in > Sign in to log in as Troy.
   
3. Navigate to the Credit Cards page once or a few times to generate clickstream data.
   
4. In your browser, return to Customer Decision Hub.
5. In the header of Customer Decision Hub, click the clipboard icon and open Customer Profile Viewer.
   
6. In the Customer ID field enter 14 and click View.
   1. On the Customer Profile Viewer page, click the Behavioral data tab.
   2. In the Summaries and aggregates list, select Financial services clickstream.
      
7. Scroll down to confirm that Card Page visit counts have increased and that additional attributes now have values.
   Note: The attribute values are calculated in real-time from your actions on the U+ Bank website, so the values vary.
   

8. In the upper-right corner, click user icon, and then Log off from Customer Decision Hub.
9. In the lower-left corner, click user icon and then Log off from Dev Studio.

6 Add financial clickstream summary predictors to AI models

1. Log in as the data scientist:
   1. In the User name field, enter DataScientist.
   2. In the Password field, enter rules.
2. In the navigation pane of Customer Decision Hub click Intelligence > Prediction Studio to launch Prediction Studio.
3. In the Predict Web Propensity prediction, click Open Prediction.
   
4. On the Models tab of the prediction, click the Web Click Through Rate Customer adaptive model.
   
5. On the Predictors tab, click Add field > Add multiple fields.
   
6. In the Current page (CDH) section, expand Page Customer.
7. Click Page FSClickstream to set the clickstream predictors.
   
8. At the top of the list, select the check box to select all predictors shipped with the component.
   Note: As models evolve, predictors with low predictive power automatically become inactive.
   

9. Click Submit.
10. In the upper right corner, click Save.

---

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

• Building the Customer Insights Cache v3

---

Available in the following mission:

• Preparation for 1:1 Customer Engagement Implementation v5