PEGACPDS24V1 Certified Pega Data Scientist (PEGACPDS24V1) Practice Questions
Prepare for PEGACPDS24V1 with more than an answer.
- Exam fee
- $190 USD
- Level
- Beginner
Domains covered on the exam 7
- AI for Customer Decision Hub8%
- Adaptive Analytics22%
- Predictive Analytics26%
- Prediction Patterns20%
- Governance2%
- Pega Process AI8%
- Pega NLP14%
- 1
A system administrator is reviewing the Adaptive Models monitoring tab in Prediction Studio. They notice several models are classified as 'Dormant'. What does this classification indicate about these specific models?
Show answer details
Correct answer: B
In Prediction Studio, a model is flagged as 'Dormant' if it has not received any response data over a configured period of time. This usually indicates that the action associated with the model is no longer being presented to customers, or there is an issue with the response capture feedback loop.
- 2
In Pega Customer Decision Hub, what is the fundamental difference in how Predictive Models and Adaptive Models are trained and deployed?
Show answer details
Correct answer: A
This is the core distinction. Predictive models require a historical dataset with known outcomes to be trained offline before they are useful. Adaptive models start with no knowledge and update their scoring algorithms dynamically (online learning) as they receive real-time accept/reject feedback from customers.
- 3
An organization is migrating their legacy churn prediction model into Pega. The existing model was developed in Python using a Gradient Boosting algorithm and exported as a standard PMML file. When setting up the prediction in Prediction Studio, how should the data scientist incorporate this external model?
Show answer details
Correct answer: C
Pega Prediction Studio natively supports the import of Predictive Model Markup Language (PMML) files, as well as H2O.ai MOJO objects. The data scientist simply imports the file, creates a Predictive Model rule, and maps the model's expected inputs to the properties available in the Pega customer data model.
- 4
A data science team wants to replace an active predictive model (Champion) with a newly developed model (Challenger) that showed better performance in offline tests. However, they want to test the Challenger in production without impacting the actual customer experience or business outcomes. Which MLOps feature in Pega Prediction Studio should they utilize?
Show answer details
Correct answer: B
In Pega MLOps, placing a Challenger model in 'Shadow Mode' allows it to run in parallel with the Champion model in production. The Shadow model receives real production data and calculates propensities, but its outputs are not used to make business decisions. This allows the team to safely monitor its real-world performance before promoting it.
- 5
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?
Show answer details
Correct answer: A
In Pega Customer Decision Hub, the standard Next-Best-Action arbitration formula prioritizes actions by multiplying Propensity (likelihood to accept), Context weighting (relevance in the moment), Action value (financial impact), and Business levers (strategic priority). This comprehensive approach ensures that both customer needs and business objectives are balanced in real-time.
- 6
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?
Show answer details
Correct answer: C
Predict Churn Risk (or Likelihood to Churn) is a standard prediction used to assess how likely a customer is to leave. This propensity is then used in arbitration to prioritize retention offers over cross-sell offers for at-risk customers.
