Testing next best action with Persona and Channel Context

This video shows you how to create Personas and Channel Contexts and how to use them for next best action testing.

U+Bank, a retail bank, is cross-selling on the web. The bank wants to test the recent next best action configurations in Customer Profile Viewer. To generate the test results of the next best action strategy framework, the bank needs to create personas and channel context.

The dedicated space for creating, updating, and managing the Personas and Channel Contexts in Customer Decision Hub is the Persona Management landing page.

A persona is a profile of a fictitious person, representing a group of customers with a similar set of attributes. There are three types of personas you can create in CDH:

• New persona, where you input the customer properties manually,
• Persona from file, when creating Personas in bulk, using an external file,
• Persona from the existing customer.

To test the next best action configurations, U+Bank decided to use the Persona created based on existing customer Troy Murphy. Troy is a 26-year-old chef, who has been a customer of the bank for over three months, with a high credit risk. Troy is also considered financially vulnerable.

It is a good practice to use such customer information to name your Persona. The descriptive naming convention helps users to recognize the profile faster and to avoid repetitive Persona profiles. Following this rule, you can name the persona created based on Troy's profile: Young High Risk Financially Vulnerable.

When you submit the new persona, the system auto-populates the actual customer information and organizes it in the customer attributes tree, which represents the Customer Insights cache. All the customer details are editable. You use this option to create the persona based on the customer, and then adjust it to specific industry needs.

In the Persona profile, you can also add a Persona description and tags.

Tags are the labels that you add to personas for the purpose of identification and easier searching. Tags can consider customer properties like Credit risk, Age, and Relationship length in days and so on, as well as engagement policy rules.

For example, if the applicability rule is Relationship length in days is =< 90, and Troy's relationship with the bank is 88 days, we can tag him as a new_customer. The tag Financially_vulnerable means that Troy does not meet the suitability condition of Is financially vulnerable=false. Low_debt means that the Debt-to-income ratio for Troy is less than or equal to 48.

Personas include only raw information about the customer. Therefore, to run the tests in context, an additional factor that contains information about the Direction, Channel, and Real-time container is necessary. This factor is called Channel context and it can also be created on the Persona Management Landing Page.

U+Bank is cross-selling on the web, therefore there is a need to perform a test for the direction Inbound and the channel Web. The real-time container for this channel context is Top_Offers.

When you create the channel context, the system automatically displays it on the Channel Context tab of the Persona Management landing page.

Pega introduces new features that use the power of Pega GenAI™ to simplify your daily tasks in Pega Customer Decision Hub.

With Pega GenAI, creating personas is effortless and efficient. When creating a new persona, you can describe the characteristics you want to include in natural language. It will allow you to create a diverse set of personas quickly that accurately represent your target audience.

In this case, you can generate customer details by typing your persona characteristics in the text box. Create a mature, low-debt, financially invulnerable customer, who lives in New York.

Based on the given details, the system generates the Customer data for the new persona. In this case, the age information provided is automatically set to 45, "low debt" corresponds to a low debt-to-income ratio, and "financially vulnerable" is translated to the "isFinanciallyVulnerable" flag being set to false.

The remaining properties are randomly filled and can be reviewed and updated as necessary.

U+Bank wants to test the next best actions using the newly created Persona and Channel context. The objective is to identify whether any actions have been filtered out for the Young High Risk Financially Vulnerable Persona and determine the reasons why.

You can proceed with next best action testing in the Customer Profile Viewer. Search for Persona Young High Risk Financially Vulnerable profile, and on the next best actions tab, make the decision for the Web Inbound Channel context.

In the action results table, you can observe that two out of four credit cards were filtered out, which means that they will not be presented to the customer.

You can explore the reasons behind this decision by utilizing the "Filtering by feature" option. The action results table has been enhanced with multiple categories that might serve as the underlying cause for excluding certain actions.

For instance, actions may be excluded based on eligibility, applicability, suitability, contact policy suppression, or if no treatment has been defined. When the labels in the table columns display "false," it indicates that the action is not excluded and can be presented to the customer.

In the case of Persona Young, High Risk, Financially Vulnerable, two actions have been filtered out due to the Suitability condition. The label in the Excluded by suitability column of the action results table indicates 'true'. Next to the label is an information icon that provides an explanation of the decision.

The Rewards Plus card and the Premier Rewards card were excluded because of the suitability condition: Is financially vulnerable=false. Young High Risk Financially Vulnerable Persona is financially vulnerable, he does not meet this condition and therefore, the two actions cannot be presented to him.

Additionally, in CPV, another GenAI feature: the AI Insight is available. It provides the summary of the tested configuration. In this example, you receive a clear explanation that there are four candidate offers for the Persona. However, only 2 actions passed, and 2 actions were filtered out due to the Suitability conditions.

By clicking on the Polaris icon for each row in the Results column, you can access an explanation of the action results in the Action results explanation window, specific to the action.
In this example, you will learn that the RewardsPlusCard is filtered out due to the suitability condition.

You have reached the end of this video. What did it show you?

- What is Persona and Channel context.

- How to create a Persona based on a customer profile.

- How to create a Persona using the Pega GenAI feature

- How to create a channel context.

- How to test the next best actions using Personas.

- How AI insights are generated using Pega GenAI.