PEGACPDS25V1

Review 50 PEGACPDS25V1 practice questions with answer explanations and community insights.

Question 1

You’re implementing a decision strategy for a telecom company’s retention program. The strategy needs to identify customers at high risk of churn and make them eligible for retention offers instead of standard promotional offers. The data scientist team has created a churn prediction for this purpose.What is the correct approach to implementing an applicability rule that shows retention offers only to customers with high churn risk?

  1. Create a decision strategy with Prediction and Filter components for high-risk customers, then apply it in the Next-Best-Action Designer’s Applicability section.
  2. Use a When rule in the Channels section to display retention offers when the customer’s predicted response is “High risk”.
  3. Configure the churn prediction to automatically add eligible customers to an audience that the retention offers target.
  4. Directly add the churn prediction to the Next-Best-Action Designer’s Eligibility section with a condition that the churn risk level equals “High risk”.

Question 2

As a data scientist, you can improve the predictive power of adaptive models by adding predictors to the models. The models automatically learn which predictors are valuable by capturing the responses.Regarding this adaptive learning process, what is the key difference between parameterized predictors and non-parameterized predictors?

  1. Unlike non-parameterized predictors, when parameterized predictors are highly correlated, they are not grouped by the system.
  2. The number of parameterized predictors is limited, while the number of non-parameterized predictors is unlimited.
  3. Only non-parameterized predictors influence propensity.
  4. There is no key difference between parameterized predictors and non-parameterized predictors.

Question 3

Which adaptive model output is automatically mapped to a strategy property?

  1. Propensity
  2. Evidence
  3. Performance
  4. Score

Question 4

By creating parameterized predictors, you can incorporate input fields that are not directly available in the customer data model into adaptive models, such as expressions, offline model scores, and online model scores. This approach enhances the ability of the adaptive models to make more informed predictions by using a broader range of predictors.What is the primary purpose of creating parameterized predictors based on expressions in the context of enhancing adaptive models in Pega Customer Decision Hub?

  1. To enable adaptive models to incorporate derived metrics.
  2. To replace the need for traditional data preprocessing methods.
  3. To directly increase the credit score of the customer based on webpage visit frequencies.
  4. To provide real-time customer feedback directly into the adaptive models.

Question 5

You can make online model scores generated by predictive models available to adaptive models as parameterized predictors.What advantage does adding online model scores as parameterized predictors offer to adaptive models in Customer Decision Hub?

  1. It enables the complete replacement of adaptive models with predictive models.
  2. It negates the need for any form of data preprocessing or feature engineering.
  3. It ensures 100 percent accuracy in predictions because of real-time data analysis.
  4. It provides adaptive models with real-time insights into customer propensities.
  5. It simplifies the model deployment process by automating all updates and integrations.
We are moving to a new platform

CertificationTest is being migrated. Some pages may be slow or briefly unavailable; everything will be back to normal within a few hours. If you run into any issue, email support@certificationtest.net.