Adding predictors to an adaptive model

3 Tasks

10 mins

Pega Customer Decision Hub 8.7

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 8.6 Pega Customer Decision Hub 8.6 Pega Customer Decision Hub 8.5 Pega Customer Decision Hub 8.4

Visible to: All users

Beginner Pega Customer Decision Hub 8.7 English

Scenario

U+ Bank is implementing cross-selling of their credit cards on the web by using Pega Customer Decision Hub™. The implementation team has set up the business taxonomy, contact policy rules, arbitration, and the real-time containers in the Next-Best-Action Designer.

After the initial setup, the team has added additional static customer profile information. Also, the team used Pega Customer Profile Designer to implement industry-specific best practice clickstream summaries. The summaries extend the customer profile with real-time behavioral data.

As a data scientist, you make this added data available to the adaptive models. Verify that the adaptive models work properly by simulating customer behavior on the U+ Bank website and monitoring the propensity for positive and negative customer behavior.

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: Configure the new predictor fields

In Prediction Studio, open the Web_Click_Through_Rate model. Validate that some of the customer properties are already configured as predictors. Enhance the predictor list with the recently added properties from the current page (Customer). From the FSClickstream page, add all fields to the customer profile.

Task 2: Verify the effect of negative customer behavior

Successively log in to the U+ Bank website as Troy and log out without clicking the offer. In the Interaction History report, notice that the propensity decreases when you do not click the offer after multiple logins.

Task 3: Verify the effect of positive customer behavior

Log back multiple times and click the offer each time to record positive behavior to prove that the artificial intelligence (AI) learns. Also verify that the propensity of the offer increases for customers with a similar profile.

 

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 new predictor fields

1. On the exercise system landing page, click Pega CRM suite.
2. Log in as a data scientist with User name DataScientist using Password rules.
3. In Prediction Studio, click the Predict Web Propensity tile to open the prediction.
4. In the Predict Web Propensity prediction, click the Models tab.
   
5. In the Supporting models section, click Web_Click_Through_Rate to open the model.
6. On the Web_Click_Through_Rate form, click the Predictors tab to view the list of already-available predictors.
   
7. On the Predictors tab, click Add field > Add multiple fields to open the Add predictors dialog box.
   1. In the Add predictors dialog box, click Current page (Customer).
   2. In the Current page (Customer) list, select the Name checkbox to select all fields.
      
   3. Click Submit to add the predictors.
8. On the Predictors tab, click Add field > Add multiple fields to open the Add predictors dialog box.
   1. In the Add predictors dialog box, expand Custom page Customer, and then click Page FSClickstream.
   2. In the Page FSClickstream list, select the Name checkbox to select all fields.
      
   3. Click Submit to add the predictors.
      Note: The FSClickstream page represents the customer behavioral data that is introduced by the system architect after installation of the Customer Profile Designer Accelerator component that is available from Pega Marketplace.

9. Click the Settings tab.
   Note: Notice that the model update frequency is set to 1. This value allows learning of the adaptive models on a very low volume of responses. In a production system, do not change the default value of 5000 without first consulting a senior data scientist.

10. In the upper-right corner, click Save.

2 Verify the effect of negative customer behavior

1. On the exercise system landing page, click U+ Bank to launch the U+ Bank website.
   
2. On the U+ Bank website, in the upper-right corner, click Log in to access the site as Troy to display an offer in the marketing banner.
   Caution: Do not click on the Learn more link at the bottom of the banner. Otherwise, the action is recorded as a positive behavior.
   Note: For this challenge, the system is configured to record a negative outcome after 60 seconds automatically. During successive logins, ensure a 60 seconds time delay.

3. Click the Polaris icon, and then notice that the propensity for the Standard card is 0.5.
   
4. Log out, and then log in as Troy.
5. Click the Polaris icon, and then notice that the propensity for the Standard card has dropped to 0.25.
   
6. Repeat steps 4-5 once more and then notice that the propensity for the Standard card has dropped to 0.16.
   

3 Verify the effect of positive customer behavior

1. Log out, and then log in as Troy.
2. Click Learn more to generate a positive response to the Standard card offer.
3. Repeat step 1-2 multiple times, and then click Learn more only when the Standard Card is displayed; otherwise, ignore the offer.
4. Click the Polaris icon when the Standard card offer is displayed.
   Notice that the propensity for the Standard card increases. The value depends on the number of times that you click Learn more.
   
   Caution: Depending on the status of the adaptive models, either Rewards Plus card, Premier Rewards card, or Standard card is presented after log in. When the customer is selected for the control group of 2%, the system generates a random propensity. Occasionally, the propensity may might not consistently go up or down.

---

---