PEGACPDS26V1 Sample Questions & Answers
Emphasizes adaptive model monitoring above everything, then covers Pega NLP text analytics, Pega Process AI, Customer Decision Hub predictions, model governance, prediction patterns, and MLOps work for building and evaluating predictive models.
Launch the full PEGACPDS26V1 simulator →Showing 6 of 12 free samples.
- Question 1Beginner
Adaptive Analytics · Adaptive models
True or False: In Pega Infinity '26, adaptive models must be taken offline periodically so that a data scientist can manually retrain them using the latest batch of customer response data.
Show answer & explanation
Correct answer: B
False. Adaptive models in Pega are self-learning. They continuously and automatically update their internal scoring algorithms in real-time as customer responses are captured, without requiring offline manual retraining by a data scientist.
- Question 2AdvancedSelect 2
Adaptive Analytics · Monitoring adaptive models
While reviewing the Adaptive Model monitor tab in Prediction Studio, a data scientist examines the Bubble chart plotting Model Performance (AUC) on the Y-axis and Success Rate on the X-axis. Several models appear clustered in the bottom-right quadrant. Which TWO conclusions can be drawn about these specific models? (Select TWO)
quadrantChart title Model Performance vs Success Rate x-axis Low Success Rate --> High Success Rate y-axis Low AUC --> High AUC quadrant-1 Stars quadrant-2 Niche quadrant-3 Dead quadrant-4 Cash Cows Model A: [0.8, 0.2] Model B: [0.9, 0.3]Show answer & explanation
Correct answers: A, C
Models in the bottom-right quadrant have a high Success Rate (X-axis) but low Performance/AUC (Y-axis). Because they have a high success rate, they are generating positive responses and driving business value. However, their low AUC indicates they are not effectively differentiating between who will and will not accept the offer, essentially acting like a static rule or benefiting from a universally popular offer.
Models in the bottom-right quadrant have a high Success Rate (X-axis) but low Performance/AUC (Y-axis). Because they have a high success rate, they are generating positive responses and driving business value. However, their low AUC indicates they are not effectively differentiating between who will and will not accept the offer, essentially acting like a static rule or benefiting from a universally popular offer.
- Question 3Intermediate
Adaptive Analytics · Adaptive models
When configuring an adaptive model in Prediction Studio, a data scientist must define the outcome mapping. If the business wants the model to predict the likelihood of a customer clicking a web banner, how should the outcomes be categorized?
Show answer & explanation
Correct answer: A
In ADM outcome mapping, the behavior you want to predict (the positive outcome) is mapped as the 'Target' behavior. The negative or non-response (such as an impression without a click, or an explicit ignore) is mapped as the 'Alternative' behavior. The model calculates the propensity of the target behavior occurring.
- Question 4Intermediate
Adaptive Analytics · Adaptive models
A data scientist adds a new categorical predictor named 'Customer_Occupation' to an adaptive model. The organization has over 1,500 distinct occupation titles in its database. How does the Adaptive Decision Manager (ADM) process this high-cardinality predictor to ensure the model remains performant and avoids overfitting?
Show answer & explanation
Correct answer: C
ADM natively handles high-cardinality categorical variables through dynamic binning. It groups symbols (categories) that exhibit similar behavior into discrete bins. If there are too many unique values with low frequency or similar behavior, they are clustered together, often resulting in a 'Residual' bin to maintain statistical significance and model performance.
- Question 5Advanced
Adaptive Analytics · Exporting adaptive model data
Case Study: A multinational insurance firm uses Pega Customer Decision Hub '26. The Chief Data Officer wants to conduct an offline longitudinal study on how the predictive power of various customer demographic attributes has shifted over the past 12 months. They require granular data showing how predictors were evaluated at different points in time.
Which combination of features and data structures should the data scientist utilize to extract this information for external BI analysis?
Show answer & explanation
Correct answer: B
The ADM Data Mart is specifically designed to store historical snapshots of adaptive models and their predictor binning statistics over time. By exporting this data from Prediction Studio, data scientists can perform deep offline analysis (using BI tools) on model performance trends and predictor evolution without impacting the real-time decisioning environment.
- Question 6Beginner
Adaptive Analytics · Adaptive models
Which underlying machine learning algorithm powers the Adaptive Decision Manager (ADM) in Pega Infinity '26 to enable real-time, self-learning predictions?
Show answer & explanation
Correct answer: C
Pega's Adaptive Decision Manager (ADM) primarily uses a proprietary implementation based on the Naive Bayes algorithm. This algorithm is highly efficient for real-time, incremental learning because it calculates probabilities based on predictor bins and updates these probabilities instantly as new responses are recorded.
Ready for the real thing?
The full PEGACPDS26V1 simulator has every exam-style question, timed mode, and instant scoring.