PEGACPDS88V1 Certified Pega Data Scientist 8.8 Questions and Answers

to use AI to route claims that are likely to miss their deadline to an expert, you need to create a prediction. A prediction is a decision management component that you can reference in a case type. A prediction uses a predictive model or an adaptive model to calculate a probability or a score for a specific outcome.

https://academy.pega.com/topic/process-ai-predictions/v1

The purpose of predictions is to build adaptive models.

An adaptive model is different from a predictive model as it can use strategy properties as predictors. Strategy properties are dynamic values that are calculated or derived during the execution of a decision strategy. They can capture customer context, such as channel, location, time, etc. References: https://academy.pega.com/module/predicting-customer-behavior-using-real-time-data-archived/topic/adaptive-models-overview

You can use one Set Property component to calculate the average margin of four actions by using an expression that sums up the margin values of each action and divides by four. You can then use this property in other components, such as Filter or Prioritize. References: https://academy.pega.com/module/creating-and-understanding-decision-strategies-archived/topic/setting-properties

The Predictive Model Markup Language (PMML) allows for predictive models to be easily shared between applications. PMML is a standard XML format that describes the input parameters, output score, and mathematical formulas of predictive models. PMML enables interoperability between different tools and platforms that support PMML, such as Pega Customer Decision Hub. References: https://community.pega.com/sites/default/files/help_v82/procomhelpmain.htm#data-/data-predictivemodel-/data-predictivemodel-pmml/main.htm

The Pega Customer Decision Hub™ delivers Next-Best-Actions consistently through multiple channels. This applies to Mobile channels.

The performance of an adaptive model that has not collected any evidence yet is 50. This means that the model is not confident about its predictions and assigns equal probability to all actions. References: https://community.pega.com/sites/default/files/help_v82/procomhelpmain.htm#rule-/rule-decision-/rule-decision-adaptivemodel/main.htm

If a strategy designer has created 10 actions in the Sales/Credit Cards group and 10 actions in the Sales/Mortgages group and would like to import all 10 actions from the Credit Cards group and only two actions from the Mortgage group into one decision strategy, the minimum number of Proposition Data components he needs to use in his strategy is three.

To predict if a customer is likely to churn, you use a model of type decision tree. A decision tree is a type of predictive model that uses a set of rules to classify customers into different categories based on their attributes and behavior. A decision tree can predict a binary outcome (such as churn or not churn) or a multi-class outcome (such as low risk, medium risk, or high risk). References: https://academy.pega.com/module/predictive-analytics/topic/using-decision-tree-models

Proactive retention is a strategy that anticipates potential customer churn and takes actions to prevent it before it happens. It uses predictive analytics to identify customers who are at risk of leaving and offers them incentives or solutions to retain them. References: https://academy.pega.com/module/one-one-customer-engagement/topic/proactive-retention

The likelihood that a proposition will be accepted by the customer is stored in the strategy property called pyBehavior. This property is calculated by an adaptive model or a predictive model and reflects the customer’s propensity to respond to an offer. References: https://academy.pega.com/module/creating-and-understanding-decision-strategies-archived/topic/using-predictions-decision

The mapping of the input fields of a third-party predictive model is done in the Predictive Model rule. The Predictive Model rule defines how to invoke and interpret the results of a third-party predictive model that is imported in PMML format. References: https://academy.pega.com/module/predictive-analytics/topic/using-pmml-models

Given the scenario where U+ Bank introduces a new credit card that has no historical customer behavior data and wants to offer this credit card on the personalized web portal, you must use an adaptive model.

Predictions combine predictive analytics and best practices in data science. Two best practices included in Pega Customer Decision Hub™ predictions are using a control group and selecting the model with the highest performance.

When capturing historical data in an adaptive model, the outcome of the interaction and the value of all predictors are captured for every customer interaction.

Up to 100 fields to limit the impact on model speed Reference:

When configuring an adaptive model, it is recommended to select up to 100 potential predictors to limit the impact on model speed.

The principle of parsimony states that from two models with similar performance, we choose the one with the fewest number of predictors. This is because a simpler model is easier to understand, maintain, and deploy. References: https://academy.pega.com/module/predictive-analytics/topic/evaluating-predictive-models