PEGACPDS88V1 Sample Questions Answers

 When you place the new model in shadow mode in the production environment, the current model still drives the prediction, but the new model runs in parallel and collects performance data for comparison. References: https://academy.pega.com/module/predictive-analytics/topic/mlops

Pega adaptive models learn about customer behavior in real time by analyzing the responses to each offer and updating their predictions accordingly. They do not require historical data, human effort, or inbound channels to function. References: https://academy.pega.com/module/predicting-customer-behavior-using-real-time-data-archived/topic/adaptive-models-overview

Predictive models need historical data to be created. Predictive models are statistical models that use historical data to learn patterns and trends and make predictions for future outcomes. Predictive models can be built with Pega machine learning or imported from third-party tools such as PMML or H2O. References: https://community.pega.com/sites/default/files/help_v82/procomhelpmain.htm#rule-/rule-decision-/rule-decision-predictivemodel/main.htm

The Switch component allows you to use a third-party Credit Risk Model 80% of the time and a Pega Credit Risk Model 20%.

Lift is a key metric for the performance of the adaptive models. To measure lift, you need a control group with random actions. Lift is the ratio of the performance of the adaptive model to the performance of the control group. A control group is a subset of customers who receive random actions instead of the ones suggested by the model. References: https://community.pega.com/sites/default/files/help_v82/procomhelpmain.htm#data-/data-adm-/data-adm-model/main.htm

When building a model using Pega machine learning, the validation hold-out set is used to train the models and to check for robustness of candidate models.

to create a prediction that calculates the probability that a claim is fraudulent, you need to create a case management prediction. This type of prediction allows you to use predictive models built on external platforms such as H2O.ai and apply them to case types in Pega Process AI™. You can then use the prediction outcome in a decision step to route claims based on their fraud risk.

https://academy.pega.com/challenge/creating-fraud-prediction/v3

Pega Decision Management Reference:

To build a predictive model, use Pega Decision Management. Pega Decision Management is a tool that enables businesses to make informed decisions based on data and analytics.

Adaptive model predictors are selected from the customer profile, which contains information about the customer’s attributes and behavior. Predictors can be either scalar or aggregate properties that capture customer context, such as channel, location, time, etc. References: https://academy.pega.com/module/predicting-customer-behavior-using-real-time-data-archived/topic/configuring-adaptive-models

Predictor selection and The update frequency of the models Reference:

As a highly experienced data scientist, you have access to advanced settings such as predictor selection and the update frequency of the models.

If you are debugging the Next-Best-Action decision strategy and want to see if the result of the Arbitration is correct, you should use the Prioritize strategy component.

The use of an imported third-party model in a decision strategy is similar to the use of a model built with Pega machine learning. You can use a predictive model component in a decision strategy to reference an imported third-party model and pass the input parameters and receive the output score. You do not need to convert the third-party model into a Pega machine learning model or Pega markup language. References: https://community.pega.com/sites/default/files/help_v82/procomhelpmain.htm#rule-/rule-decision-/rule-decision-predictivemodel/main.htm

Customer properties are used to map predictors to customer data that is available in the system. They can be either scalar or aggregate properties. References: https://academy.pega.com/module/creating-and-understanding-decision-strategies-archived/topic/mapping-predictors-customer

As a data scientist, if you are tasked with configuring two predictions that are driven by an adaptive model, you need to pay extra attention to adaptive model settings.

As a data scientist, you create a prediction that calculates the probability that a client is likely to cancel a subscription. The type of prediction you create is Customer Decision Hub.

Pega Customer Decision Hub™ uses the PCV*L arbitration formula to select the next best action for each customer. The purpose of the formula is to balance customer needs with business objectives.

 When building a predictive model, the Data Analysis stage is where you select the input data that will be used to train and test the model. You can also filter, group, or transform the input data to improve its quality and relevance. References: https://academy.pega.com/module/predictive-analytics/topic/analyzing-data

A predictive model is a mathematical function that estimates the probability of an outcome based on input data. When building a predictive model, the use of testing and validation samples increases the accuracy of models123. Testing and validation samples are subsets of data that are used to evaluate how well a model performs on new data that was not used to train the model. Testing and validation samples help prevent overfitting, which is when a model learns too much from the training data and fails to generalize to new data.

In Prediction Studio, the key metrics of adaptive models are visualized in a bubble chart. The three key metrics displayed in this chart are number of responses, propensity of the model, and performance of the model.

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

Positive and negative behavior Reference:

To configure an adaptive model, you must identify positive and negative behavior that indicate specific customer behavior.

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

The purpose of predictions is to build adaptive models.

Adaptive models perform a binary model calculation. This means that adaptive models predict the likelihood of a positive or negative response for each action and customer profile. Adaptive models do not require underlying predictive models or historical data sets to start learning. They learn from customer responses in real time and continuously update their predictions. References: https://community.pega.com/sites/default/files/help_v82/procomhelpmain.htm#rule-/rule-decision-/rule-decision-adaptivemodel/main.htm

The filter component is used to filter actions based on various criteria, such as eligibility, suitability, priority, or custom conditions. References: https://academy.pega.com/module/creating-and-understanding-decision-strategies-archived/topic/filtering-actions

To detect the sentiment of the incoming emails, you need to configure a text analytics prediction1234 in Prediction Studio. A text analytics prediction is a type of prediction that uses natural language processing (NLP) to analyze text data and extract insights, such as topics, entities, and sentiments. You can use a text analytics prediction to detect the sentiment of an email based on its content and assign a score ranging from -1 (negative) to 1 (positive). This can help you improve the customer experience by identifying dissatisfied customers and taking appropriate actions.

 The Monte Carlo method enables the company to generate data that simulates customer behavior and can be used as input for adaptive decisioning. The generated data is based on predefined probabilities and distributions that reflect realistic scenarios. References: https://academy.pega.com/module/demonstrating-adaptive-learning-archived/topic/creating-monte-carlo-data-set

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

A scorecard model is a type of predictive model that allows you to monitor the real-time performance of a third-party churn model. A scorecard model compares the predicted churn probability with the actual churn outcome and calculates a performance score for each customer segment. References: https://academy.pega.com/module/predictive-analytics/topic/using-scorecard-models

In Prediction Studio, model transparency thresholds can be set for a model.

One of the types of analysis that occurs during natural language processing is Semantic analysis.

You are a company with a new and unique product, and you want to offer it to the right customer. Given the scenario, you should use an adaptive model rule type. An adaptive model rule type allows you to define the predictors and the outcome of the model and associate it with an action. An adaptive model learns from customer responses in real time and predicts the propensity of each customer to accept the action. An adaptive model is suitable for new products or markets where there is no historical data available. References: https://community.pega.com/sites/default/files/help_v82/procomhelpmain.htm#rule-/rule-decision-/rule-decision-adaptivemodel/main.htm

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

 The most important aspects taken into consideration when determining the Next-Best-Action are business objectives and customer needs. Business objectives reflect the goals and priorities of the organization, such as increasing revenue, reducing costs, or managing risk. Customer needs reflect the preferences and expectations of the customers, such as their interests, intents, or life events. References: https://academy.pega.com/module/one-one-customer-engagement/topic/next-best-action-designer

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.

The Monte Carlo method is a way to create a data set that includes mock-up customer data. You can use this method to generate random values for customer properties, such as age, gender, income, etc., based on predefined probabilities and distributions. References: https://academy.pega.com/module/demonstrating-adaptive-learning-archived/topic/creating-monte-carlo-data-set

Adaptive models can start to learn without historical evidence. The starting propensity of every action is 0.5.

When you increase the performance threshold setting of an adaptive model rule, the number of active predictors may decrease. The performance threshold is the minimum performance that a predictor must have to be included in the model. If you increase this value, some predictors may not meet the criteria and be excluded from the model. References: https://community.pega.com/sites/default/files/help_v82/procomhelpmain.htm#rule-/rule-decision-/rule-decision-adaptivemodel/main.htm