Importing predictive models

1 Task

10 mins

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 8.5

Visible to: All users

Beginner Pega Customer Decision Hub '23 English

Scenario

U+ Bank implements Pega Decision Management but already uses predictive models that an external bureau created. You are asked to make an existing H2O model actionable in Pega Customer Decision Hub™. The model is based on historical customer interactions with the bank and predicts the likelihood that a customer might churn soon.

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: Import an H2O model

In Prediction Studio, create a predictive model rule by using the ChurnH2O.zip model file.

 

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 Import an H2O model

1. Download the ChurnH2O model file to your local machine.
2. On the exercise system landing page, click Launch Pega Infinity™ to log in to Customer Decision Hub.
3. Log in as a data scientist:
   1. In the User name field, enter DataScientist
   2. In the Password field, enter rules.
4. In the Work from 1:1 Operations Manager section, click CR-1 to open the change request.
5. In the Scope of changes section, click Create, and then select Decision > Predictive model.
6. In the Predictive Model Record Configuration section, in the Label field, enter ChurnH2O.
7. In the Context section, in the Apply to field, enter or select UBank-CDH-Data-Customer.
8. In the upper-right corner, click Create and open to configure the new predictive model.
9. Click Create new model to start the model configuration.
10. In the Create Predictive Model dialog box, click the Import model tab.
11. Click Choose File, and then, on your local machine, select the ChurnH2O.zip model file.
12. Click Next to proceed to the Outcome definition section.
13. In the Outcome definition section, ensure that Predict the probability to is set to Churn. Do not alter the advanced settings.
14. In the Expected performance (AUC) field, enter 80.
    
15. Click Import to import the model file.
16. On the Mapping tab, verify that all predictors of the model are correctly mapped to the fields of the data model.
    
17. Click Save to save the model.
     

---

---

Available in the following mission:

• AI for 1:1 Customer Engagement v3