QUESTION: 53

When building a predictive model, what is a valid predictor data type?

Symbolic
Boolean
String
Character

Answer(s): B

Explanation:

When building a predictive model, a valid predictor data type is Boolean, which can have only two values: true or false. Other valid predictor data types are numeric, date, and symbolic (categorical).

Reference:

https://academy.pega.com/module/predictive-analytics/topic/predictor-data-types

Reveal Solution Next Question

QUESTION: 54

Which two factors do you inspect to assess the general health of the adaptive models in Prediction Studio? (Choose Two)

Model transparency
Insights________________
Performance of the models
Number of decisions

Answer(s): C,D

Explanation:

To assess the general health of the adaptive models in Prediction Studio, you can inspect the performance of the models and the number of decisions. The performance of the models shows how well they predict customer behavior over time. The number of decisions shows how much data is available for each model to learn from.

Reference:

https://academy.pega.com/module/predicting- customer-behavior-using-real-time-data-archived/topic/monitoring-adaptive-models

Reveal Solution Next Question

QUESTION: 55

To enable an assessment of its reliability, the Adaptive Model produces three outputs: Propensity, Performance and Evidence. The performance of an Adaptive Model that has not collected any evidence is_________.

1-0
null
0.5
0.0

Answer(s): C

Explanation:

When an adaptive model has not collected any evidence, its performance is 0.5, which means that it has no predictive power and is equivalent to a random guess. As more evidence is collected, the performance can increase or decrease depending on how well the model predicts customer behavior.

Reference:

https://academy.pega.com/module/predicting-customer-behavior-using-real-time-data- archived/topic/adaptive-models-overview

Reveal Solution Next Question

QUESTION: 56

When defining outcomes for an Adaptive Model you must define

only negative behavior values
positive, negative and neutral behavior values
one or more positive behavior values
behavior values to be ignored

Answer(s): C

Explanation:

When defining outcomes for an adaptive model, you must define one or more positive behavior values, which indicate that the customer accepted or responded to the offer. You can also define negative and neutral behavior values, but they are optional.

Reference:

https://academy.pega.com/module/predicting-customer-behavior-using-real-time-data- archived/topic/configuring-adaptive-models

Reveal Solution Next Question

Free PEGACPDS88V1 Exam Braindumps (page: 14)

QUESTION: 53

Explanation:

Reference:

QUESTION: 54

Explanation:

Reference:

QUESTION: 55

Explanation:

Reference:

QUESTION: 56

Explanation:

Reference: