Exporting historical data

4 Tasks

15 mins

Pega Customer Decision Hub 8.6

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 Pega Customer Decision Hub 8.5

Visible to: All users

Beginner

Pega Customer Decision Hub 8.6

English

Scenario

U+ Bank has implemented Pega Customer Decision Hub™ to display a personalized credit card offer to eligible customers on their website. As a data scientist, you want to export the raw data used by the Web Click Through Rate adaptive model that aims to optimize the click through rate of the web banners that contain the credit card offers.

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

Role	Username	Password
Data scientist	DataScientist	rules
System architect	CRMDecisioningAdministrator	install

Your assignment consists of the following tasks:

Task 1: Configure the recording of historical data

Change the settings of the Web Click Through Rate adaptive model to enable the recording of historical data generated by the model. Set the sample percentage for both positive and negative responses to 100%.

Task 2: Create a data set

Create a new data set and set the Apply to class to PegaCRM-Data-Customer and Add to ruleset to Pega-CRM-Artifacts. Map the data set to the file in the repository that contains the historical data.

Task 3: Trigger the creation of customer interaction records

On the U+ Bank website, log in multiple times and generate two negative responses by ignoring the banner and one positive response by clicking on the offer.

Task 4: Export the data set and examine the JSON file

In Dev Studio, export the data set. The data set is exported in the JSON format. Examine the file by answering the following questions:

• In the first record, who is the customer, what is the treatment the customer received and what is the outcome of the interaction?
• How many predictors have a captured value, and how many predictors are configured in the adaptive model of the first record? What explains the difference?

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 Configure the recording of historical data

1. Log in as a data scientist with user name DataScientist and password rules.
2. In the left navigation pane, click Intelligence > Prediction Studio > Models.
3. Click Web_Click_through_Rate to open the model.
   
4. On the Settings tab, in the Model update frequency section, note that the model is set to update to update after one response.
   Note: This frequency setting is for demonstration purposes only. A web banner typically has a very high number of customer interaction and should be updated after a significant number is reached.

5. In the Recording historical data section, mark Recording historical data as active.
6. Confirm that the sample percentage for both Clicked and NoResponse are set to 100%.
   
   Note: A web banner typically has a very high number of negative responses, so for these items, a low sampling percentage is appropriate. For demonstration purposes, the sample percentage for NoResponse is set to 100%.

7. In the upper right, click Save.

2 Create a data set

1. In the left navigation pane, click Data > Data sets.
2. In the upper right, click New.
3. Configure the data set with the following information:

• Name: ADMPayload
• Type: File
• Apply to: PegaCRM-Data-Customer
• Add to ruleset: Pega-CRM-Artifacts
• Ruleset version: 01-01-99

4. Click Create.
   
5. In the Connection section, select the defaultstore repository.
6. In the File configuration section, set the file path to ADM/Rule-Decision-AdaptiveModel/Data-Decision-Request-Customer/Web_Click_Through_Rate/records*.json.
7. Click Save.

3 Trigger the creation of customer interaction records

1. On the Customer Engagement & Analytics landing page, click U+ Bank.
2. In the upper right, log in as customer Troy.

Tip: The first time that you log in, a generic offer is shown, and it may take several minute to display the credit card offer. After the first login, the credit card offer is displayed immediately when you log in again.

3. Ignore the offer and log out.
4. Log in as customer Barbara.
5. Ignore the offer and log out.
6. Log in as customer Joanna.
7. On the banner, click Learn more.
8. Return to Prediction Studio.
9. In the lower left, click DS and log off.

4 Export the data set and examine the JSON file

1. Log in as a system architect with user name CRMDecisioningAdministrator and password install.
2. In the upper right, search for ADMPayload.
3. Click ADMPayload.
4. In the upper right, click Actions > Export.
5. In the Export data set dialog box, click Export.
   Note: It may take several minutes to populate the data set. If the number of processed records does not match the number of logins, close the Export data set dialog box and retry.

6. Click Download file.
   

Caution: If you use the Google Chrome browser, right-click the link and select Save link as. click Keep in the chrome notification about the security issue.

7. Save the ZIP file locally and extract the data.json file.
8. Open the data.json file in a text editor that displays the JSON format correctly .

Tip: There are many (online) options available on the internet, such as Notepad++.

Question – In the first record, who is the customer, what is the treatment the customer received, and what is the outcome of the interaction?

Tip: The name of the customer is recorded as the Customer_pyFirstName property, the treatment is recorded as the Context_Treatment, and the outcome is recorded as the Decision_Outcome property.

Question – How many predictors have a captured value, and how many predictors are configured in the adaptive model of the first record? What explains the difference?

9. In the JSON file, count the predictors for which a value has been recorded.
10. Return to Dev Studio.
11. In the lower left, click CA and log off.
12. Log in as a data scientist with user name DataScientist and password rules.
13. In the left navigation pane, click Intelligence > Prediction Studio > Models.
14. Click Web_Click_through_Rate to open the model.
15. On the Predictors tab, note the number of configured fields.

Tip: The number of predictors for which a value is recorded is much lower than the number of potential predictors configured in the model. The model only activates predictors that perform above the threshold configured on the Settings tab.

---

---