PEGACPDS24V1 sample questions

Question 1

A retail bank is implementing Pega Customer Decision Hub to optimize their 1:1 customer engagement strategy. During the arbitration phase, the Next-Best-Action (NBA) engine must determine the final priority of various credit card offers. Which combination of factors does the standard NBA arbitration formula use to rank these offers?

Accepted Answer

Propensity, Context weighting, Action value, and Business levers

Answer

Engagement policies, Propensity, Ethical bias, and Eligibility

Answer

Model performance (AUC), Action value, Channel preference, and Propensity

Answer

Customer intent, Propensity, Action value, and Transparency threshold

Question 2

A marketing team is relying on Pega Customer Decision Hub's out-of-the-box predictions to drive their retention campaigns. They want to ensure that the AI automatically identifies customers who are at risk of leaving so that proactive retention offers can be prioritized. Which out-of-the-box prediction directly provides this capability?

Accepted Answer

Predict Churn Risk

Answer

Predict Action Propensity

Answer

Predict Web Click

Answer

Predict SLA Breach

Question 3

True or False: In Pega Customer Decision Hub, engagement policies (such as Eligibility and Applicability) are evaluated after AI models calculate the propensity for all available actions to ensure the highest propensity offer is always presented.

Accepted Answer

False

Answer

True

Question 4

A data scientist is monitoring a newly launched adaptive model in Prediction Studio. The model is intended to predict the likelihood of a customer accepting a premium credit card offer. Because the model was launched with no historical data, it currently relies on self-learning. What underlying mathematical approach does the Adaptive Decision Manager (ADM) use to update the model's scoring dynamically as new customer responses arrive?

Accepted Answer

Bayesian Scoring / Naive Bayes

Answer

Gradient Boosting Decision Trees

Answer

Deep Neural Networks (DNN)

Answer

K-Means Clustering

Question 5

When reviewing the performance of an adaptive model in the Prediction Studio Bubble Chart, a data scientist notices that a specific model has a very high success rate (Y-axis) but a low model performance / AUC (X-axis). What is the most likely business implication of this scenario?

```mermaid
quadrantChart
title Adaptive Model Bubble Chart Analysis
x-axis "Low Performance (AUC)" --> "High Performance (AUC)"
y-axis Low Success Rate --> High Success Rate
quadrant-1 High Value / Needs Review
quadrant-2 Optimal Models
quadrant-3 Dormant / Poor Models
quadrant-4 Niche / Target Refinement
Current Model: [0.2, 0.8]

```

Accepted Answer

The action being offered is universally appealing or perhaps too generous, meaning the AI cannot distinguish between different customer profiles because almost everyone accepts it.

Answer

The model has successfully identified the niche target audience, and no further action is required as the success rate is high.

Answer

The model is receiving too few responses to learn effectively, causing the success rate to artificially inflate.

Answer

The predictors selected for the model are highly correlated, causing the AUC to drop while maintaining a high overall conversion rate.

Answer

The ethical bias check has triggered a transparency threshold, artificially capping the model's predictive power.

Question 6

A consultant is optimizing the predictors for an adaptive model in Pega Customer Decision Hub. They notice that the ADM automatically organizes similar predictors into clusters. What is the primary purpose of predictor grouping in Pega Adaptive Decision Manager?

Accepted Answer

To resolve issues with highly correlated predictors by selecting only the best-performing predictor from each group to calculate the propensity.

Answer

To group customers with similar demographic profiles into a single segment for batch processing.

Answer

To ensure that ethical bias checks are applied equally across all predictor categories.

Answer

To convert unstructured text data from NLP models into structured categorical predictors.

Top vendors

Top exams

Free PEGACPDS24V1 sample questions

True or False: In Pega Customer Decision Hub, engagement policies (such as Eligibility and Applicability) are evaluated after AI models calculate the propensity for all available actions to ensure the highest propensity offer is always presented.

A consultant is optimizing the predictors for an adaptive model in Pega Customer Decision Hub. They notice that the ADM automatically organizes similar predictors into clusters. What is the primary purpose of predictor grouping in Pega Adaptive Decision Manager?

6 more free samples are waiting