Action prioritization with AI

This demo shows you how AI-based arbitration works and explains how AI predicts customer behavior. 
U+ Bank, a retail bank, uses Pega Customer Decision Hub to display marketing offers to customers on its website. The bank wants to display more relevant offers to customers based on their behavior. There is an initial set of actions that belong to Grow Issue and Credit Cards Group created in Customer Decision Hub.

After filtering by Engagement Policies, customer Troy is eligible for two credit card offers – Standard Card and Rewards Card. When he logs into the bank's website, he sees the Standard Card offer. When you click the Polaris icon next to the card offer, you can examine the arbitration details, such as propensity value and priority value.

The offer presented to the customer is the one with the highest priority that the Pega Customer Decision Hub selects based on the arbitration settings. You define the Arbitration settings in the Next-Best-Action Designer of Customer Decision Hub. The purpose of arbitration aims is to balance customer relevance with business priorities. The system uses four components of arbitration, Propensity (P), Context weighting (C), Business value (V), and Business levers (L), represented by numerical values, to achieve this balance. With the P*C*V*L formula, Customer Decision Hub arrives at a prioritization value, which the system uses to select the top offers.

Typically, the propensity for every action starts at 0.5 or 50 percent, the same as the flip of a coin. This value is the default because the AI has no past customer behavior on which to base its predictions. After every interaction, the propensity increases or decreases accordingly.

The Standard Card that is displayed for the customer Troy shows the propensity and priority equal 0.32, and it means that the system captured several interactions before.

Consider the following interaction as an example: Troy logs in multiple times and sees the same Standard Card offer. On the first three visits, Troy ignores the offer. When he visits the website the fourth time, he clicks the offer to learn more.

In Customer Profile Viewer, you can examine Troy's interactions, the decision history, and the next best actions. First, load the decision history for the current use case to view the interactions recorded. In the table, the propensity changes after the system records each interaction. You can examine that the propensity decreases because Troy ignored the offer three times. Then, after he clicked Learn more, the propensity increased.

The configuration of the AI model behind these offers treats impressions that do not result in a click as a negative outcome. As a result, the propensity, and therefore the priority of that offer, decreases. The propensity and priority of the not-clicked offer keep decreasing until the model records a click (positive outcome). However, if Troy clicks the offer, the propensity and priority increase. Next, view the next-best-action recommendations to learn more about the action for which Troy qualifies. For the current use case, the direction is Inbound, and the channel is the Web. TopOffers is the real-time container service that manages communication between the Customer Decision Hub and the website of the bank.

Based on the engagement policy rules, Troy is eligible for two credit card offers: the Standard card and the Rewards card. In Customer Profile Viewer, you can examine the arbitration factors using one of the following options: Explain prioritization, Explain weighting, or Explain propensity. In the Explain propensity view, you can check the influencing factors of a specific action for which Troy qualifies. The factors are the best-performing predictors that contribute positively to the propensity of the offer and the predictors that contribute negatively to the propensity of the offer.

Customer Decision Hub calculates the propensity for each treatment. To understand how this works, study the Analytical model behind a treatment. This pop-up window provides a summary of the AI behind the treatment. In Customer Decision Hub, the AI that determines the propensity for positive behavior towards an action or treatment is an adaptive model.

From here, you can navigate to the adaptive model in Prediction Studio, a workspace used to manage AI models. On the landing page of the Prediction Studio, every action is represented as a separate bubble on the bubble chart. Under the chart, separate Model reports for every action are available.

An adaptive model is a self-learning predictive model that uses machine learning to calculate propensity scores. It automatically determines the factors that help in predicting customer behavior. These predictors can include a customer's demographic details, product and service usage, past interactions with the bank, and even contextual information such as the current channel of interaction. In the Predictor report, you can examine the performance of individual predictors. For example, you can see how the system automatically groups the values of a numeric predictor into bins and how the propensity to accept varies across the bins.

The behavior of one customer influences the propensity calculation for other customers with a similar profile.

• You have reached the end of this video. You have learned:
• How customer behavior influences the Propensity value.
• Where in CDH you can update the Arbitration settings.
• How customer behavior and next best actions are displayed in Customer Profile Viewer.
• What are the adaptive models, and how to manage them.