Most Recent Pegasystems PEGAPCDC87V1 Exam Dumps

To automatically pause actions that are shown too often for a specific time period, you need to define suppression rules in Pega Customer Decision Hub. Suppression rules allow you to put an action on hold after a specific number of outcomes, such as views or clicks, have been recorded over a defined period. This helps prevent overexposure and ensures a better customer experience by limiting how frequently the same action is shown to a customer.

To address the issue where customers have ignored a particular mortgage offer and the bank wants to offer the action 30% more frequently, we need to configure the appropriate arbitration factor in Pega Customer Decision Hub.

Arbitration Overview: Arbitration in Pega CDH determines how actions are prioritized and selected for presentation to the customer. It involves factors like business value, propensity, and action weighting.

Action Weighting: Action weighting is used to adjust the frequency and priority of specific actions. By increasing the action weighting, you effectively make the action more likely to be selected during the arbitration process.

Implementation:

Navigate to the Next-Best-Action Designer in Pega CDH.

Locate the action for the mortgage offer that needs increased frequency.

Adjust the action weighting to increase by 30%. This adjustment modifies the priority calculation, making the action more likely to be selected.

Refer to the Pega Customer Decision Hub User Guide 8.5, section on 'Understanding Next-Best-Action Designer arbitration' which explains how action weighting influences the prioritization of actions.

Requirement:

U+ wants to show a retention offer to customers likely to leave the bank based on historical interaction data.

Model Types:

Entity Model: Used for recognizing entities within data.

Text Analytics Model: Used for analyzing text data.

Predictive Model: Used for making predictions based on historical data.

Adaptive Model: Used for real-time adaptation based on new data.

Suitable Model:

For predicting customer churn (likelihood of leaving), a predictive model is best suited because it leverages historical data to make future predictions.

Verification from Pega Documentation:

Pega documentation on leveraging predictive models for customer retention and churn analysis.

Introduction to Prioritize Component:

The Prioritize component in Pega Decisioning is used to order actions based on specific criteria.

This component evaluates the importance or priority of different actions to determine which should be executed first.

Understanding Propensity:

Propensity is a prediction of the likelihood that a customer will respond positively to a particular action.

It is a key factor in decision-making processes as it reflects the customer's predicted behavior based on past interactions and other data.

Role of Propensity in Prioritize Component:

The primary function of the Prioritize component is to rank actions.

This ranking is typically based on the propensity value, which is calculated using predictive models.

The action with the highest propensity is considered the top action because it has the highest predicted likelihood of a positive customer response.

Verification from Pega Documentation:

According to Pega's guidelines on creating and understanding decision strategies, propensity is a standard and recommended metric for prioritizing actions within the Prioritize component.

Traditionally, segments were used to identify the target audience for a campaign. In the always-on approach, segments translate into engagement policies and AI. Engagement policies define when specific actions or groups of actions are appropriate for customers, while AI-driven decisions help determine the most relevant next best actions for individual customers based on predictive and adaptive analytics. This approach ensures that each customer interaction is highly personalized and contextually relevant.

Engagement policies and their types: eligibility, applicability, suitability, and contact policy (Page 35-36)

AI models strategy and outcome optimization (Page 29-30)