Free PEGACPDS88V1 sample questions

Correct answer: The Decision Strategy within the 'Brain'

In the Pega CDH architecture, the 'Brain' represents the decisioning logic where Decision Strategies run. These strategies combine propensity scores, context, and business rules to arbitrate and select the Next-Best-Action in real-time.

Correct answer: Prediction Studio

Prediction Studio is the dedicated workspace for data scientists to build, train, and monitor predictive and adaptive models, as well as manage text analytics and third-party model integrations.

Correct answer: It measures the correlation between a single predictor and the outcome, expressed as a percentage (0-100) based on the Area Under the Curve (AUC).

Predictor Power in Pega is a metric (typically Gini derived from AUC) that quantifies the ability of a specific predictor to differentiate between positive and negative outcomes. It ranges from 0 (random) to 100 (perfect prediction).

Correct answer: It uses a 'Cold Start' mechanism, often starting with a base propensity (e.g., 0.5) and rapidly adjusting as the first pieces of evidence arrive.

ADM is designed to handle the 'Cold Start' problem. Initially, when evidence is zero, it assigns a starting propensity (often 0.5 or a configured prior) and updates the model bins immediately with every new response, allowing the model to learn rapidly from the very first interaction.

Correct answer: The 'Customer_ID' field contains too many unique values (high cardinality), making it statistically insignificant for predicting general behavior.

ADM automatically evaluates predictors. Fields like unique IDs (high cardinality) are generally useless for prediction because they don't generalize. ADM detects this lack of correlation with the outcome and assigns a power of 0.

Correct answer: The predictor is highly predictive (high AUC) and is frequently present in the data (high support).

In the ADM Bubble Chart, the X-axis typically represents Performance (AUC) and the Y-axis (or bubble size/position context) represents Importance/Frequency. A bubble in the top-right indicates a 'Star' predictor: it is both highly predictive and applies to a large portion of the cases.

Correct answer: ADM groups correlated predictors and only uses the one with the highest performance from the group for the active model scoring.

ADM performs automatic predictor grouping. It identifies correlated predictors and groups them. During scoring, it typically selects the 'best' predictor from each group to avoid multicollinearity issues and improve model robustness.

Correct answer: The model has no predictive power and is no better than a random guess.

An AUC of 0.5 indicates a random classifier. It means the model cannot distinguish between positive and negative classes any better than flipping a coin. A good model typically has an AUC > 0.6 or 0.7.

Correct answer: The 'Model Update Frequency' is configured on the Model rule form, but the actual update happens periodically based on the ADM service snapshot interval.

While ADM collects data in real-time, the actual re-computation of the binning and probabilities (the 'update') happens periodically. This is controlled by system settings to balance performance and freshness, often defaulting to a set time interval or response count threshold.

Correct answer: Add 'Rejected' as a negative outcome in the Adaptive Model rule and potentially assign it a higher weight if the version supports weighted outcomes.

In the Adaptive Model configuration, you define positive and negative behaviors. You can map 'Rejected' to the negative outcome category. While standard ADM treats all negatives similarly (binary target), advanced configurations or strategy logic can sometimes weight these, but primarily you ensure 'Rejected' is explicitly mapped as a negative outcome alongside 'Ignored'.