TEST SUPPRIMÉ, VOUS POUVEZ ÊTRE INTÉRESSÉ PAR : Pega DS 1
COMMENTAIRES |
STATISTIQUES |
RECORDS
|
|---|
EFFECTUER UN TEST
|
Titre du test:
Pega DS 1 Description: Pega Data Scientist Auteur:
Date de création: 04/10/2024 Catégorie: Autres Questions numériques : 50 |
PARTAGER LE TEST
Commentaire
Il n'y a aucun commentaire sur ce test.
Ordre du jour :
|
To predict if a customer is likely to churn you use a model of type champion challenger decision tree switch decision table. A company wants to simulate decisions that requires large amounts of data. However, the organisation's live data is inaccessible. Your advice is to use a Monte Carlo data set. The Monte Carlo method enables the company to generate random data for most of its application needs generates data that the company can use as input for adaptive decisioning combines external data sets into a larger data set makes the organization's live data accessible. MyCo, a telecommunications company, wants to implement one-to-one customer engagement using Pega Customer Decision Hub™. Which three of the following real-time channels can the company use to present Next-Best-Actions? (Choose Three) Call center Billboard on the company building Retail store SMS Traditional television advertisements. To measure the boost in success rate AI generates, you need a control action that is offered to random customers a control action that is offered to a fixed group of customers a control group of customers that receive a standard action a control group of customers that receive a random action. What is the most accurate description of proactive retention? Proactive Retention_______ simplifies the process of retaining customers enables business to respond to customers when they contact a call center anticipates potential customer churn enables the business to reduce the number of credit risk customers. The adaptive model component in a decision strategy computes A single propensity value for all actions A unique accept rate for each action A single accept rate for all actions A propensity value for each action. The decision components used on the strategy canvas are interconnected by arrows. What does a solid arrow from a "Set Property" component to a "Filter" component mean? To evaluate the "Set Property" component, the "Filter" component is evaluated first. There is a one-to-one relationship between a "Set Property" and a "Filter" component. A property from the "Set Property" component is referenced by the "Filter" component. Information from the "Set Property" component is copied over to the "Filter" component. To confirm the continuing accuracy of your adaptive models, adaptive models must be regularly inspected. Which two tasks are part of a regular inspection? (Choose Two) Update the models Check the performance and success rate of the models Adjust the advanced settings Check the performance of individual predictors Add the historical data collected since the last inspection. Predictive Analytics is a________________ real time predictive dashboard method of visualizing our data___________________ science concerned with finding repeatable patterns in query, reporting and a search tool. The likelihood that a proposition will be accepted by the customer is stored in the strategy property called _________________ ? pyPropensity pyBehavior pyProbability pyLikelihood. What is the key component of a Next-Best-Action strategy? Predictive model Decision table Strategy Work flow. Model transparency is becoming an important requirement for many businesses. In Prediction Studio, model transparency thresholds can be set for a model type a model a business issue a department. A contact center application recommends relevant actions for each customer. The business team wants to know the possible ways in which these actions can be ordered so that the contact center agent can discuss one proposition at a time, starting from the top. As a strategy designer, what are your two options if you use a Prioritize component to order the actions? (Choose Two) In a random order In alphabetical order based on the action name In descending order based on a numerical value In ascending order based on a numerical value. Two results of an adaptive model are Priority and Propensity Priority and Evidence Propensity and Performance Propensity and Rank. When developing a predictive model, the outcome value of a continuous model type can represent _________________. customer churn acceptance of an offer customer loan default the purchase value of an offer. You have created a predictive model using R and have exported it to Predictive Model Markup Language (PMML). Which component in a decision strategy do you use to leverage the PMML model? Decision tree Predictive model Third-party model Scorecard model. In a decision strategy, which component is necessary to enable access to primary customer properties? Customer Import Set Property Data Import None; customer properties are available. An Adaptive Model instance is created when you ________________. import an Adaptive Model definition rule execute the strategy that contains the Adaptive Model component create an Adaptive Model rule configure an Adaptive Model decision component. Which statement about the expected performance of a binary model is correct? The expected performance is calculated automatically when using Pega machine learning The expected performance of a binary model can range from 0 to 100 The expected performance must be set before the model can be deployed It is an optional field. The purpose of model templates when using Pega machine learning is ____________. to streamline model development to streamline model deployment to set the model contex to set the model outcomes. Which statement about Pega AI is correct? Pega AI is primarily based on self-learning models. Pega AI is primarily based on models newly build in Prediction Studio. Pega AI is restricted to models newly build in Prediction Studio. Pega AI is restricted to self-learning models. U+ Bank, a retail bank, offers the Standard card, the Rewards card and the Rewards Plus card to its customers. The bank wants to display the banner for the offer that each customer is most likely to click; therefore, their Arbitration uses Propensity from the AI models. If you are debugging the Next-Best-Action decision strategy, which strategy component will show you if the result of the Arbitration is correct? Group By Filter Set Property Prioritize. A strategy designer has created 10 actions in the Sales/Credit Cards group and 10 actions in the Sales/Mortgages group. He would like to import all 10 actions from the Credit Cards group and only two actions from the Mortgage group into one decision strategy. What is the minimum number of Proposition Data components he needs to use in his strategy? one two three twelve. The success rate of the Control group is expected to be _____________. higher than the success rate of the Test group similar to the success rate of the Test group a constant value lower than the success rate of the Test group. When predictors have a similar predicting performance, they are automatically grouped. What happens when predictors are grouped? One predictor is used by the model, the others are deactivated. One predictor is used by the model, the others are deleted. All predictors are used by the model. The predictors are merged into one. The purpose of regular inspection is to detect factors that negatively influence the performance of the adaptive models and the success rate of the actions. Which two issues should be discussed with the business? Predictors that are never used. Predictors with a low performance. Actions that have a low number of responses. Actions that are offered so often that they dominate other actions. Actions for which the model is not predictive. The standardized model operations process (MLOps) lets you replace a low-performing predictive model that drives a prediction with a superior one. When you place the new model in shadow mode in the production environment, the current model___________ uses the outcomes of the new model as predictors is automatically replaced drives the prediction no longer drives the prediction. Which statement about the PMML standard is correct? The PMML standard is designed to facilitate the exchange of models between applications The PMML standard can only be used to describe tree, scorecard and regression models. The PMML standard is a proprietary standard The PMML standard is designed to facilitate the exchange of scores between applications. Adaptive model components can output__________ An option___________ An optimized strategy The number of customer's eligible for an action The customer's propensity to accept an action. Proactive retention is applicable when a customer is Initiating contact to churn A high value customer In a collections process Likely to churn. Which value is output by an Adaptive Model? Score Performance Behavior Lift. The result of a Predictive Model is stored in a property called__________. pyPrediction pxResult pyOutcome pxSegment. The objective of Pega Process AI™ is to interpret the incoming data and then decide on the best action to take. In which two ways can you better analyze the incoming data? (Choose Two) Event processing Text analytics Business rules Decision strategies Predictive analytics. Predictions combine predictive analytics and best practices in data science. Which two best practices are included in Pega Customer Decision Hub™ predictions? (Choose Two) Setting the response timeout Selecting the model with the highest performance Selecting the audience Using a control group. What is the difference between classification and regression in Predictive Analytics? Classification is used for predicting continuous outcomes, while regression is used for predicting categorical outcomes Classification is used for predicting categorical outcomes, while regression is used for predicting continuous outcomes Classification and regression are the same thing Neither classification nor regression are used in Predictive Analytics. In a decision strategy, which component is required to enable access to proposition properties? Proposition Data Data Include Data Join Property Import. Which of the following is NOT a use case for NLP in Pega? Sentiment analysis Text classification Speech recognition Entity extraction. What are two results of an Adaptive Model? (Choose Two) Priority Propensity Segment Performance. When during a customer interaction should a Next-Best-Action decision be made? Every time new information is received When the customer intent is captured First time the customer is shown a banner At the beginning of customer call. Which of the following is a technique used in NLP for text classification? SVM (Support Vector Machines) K-Means Random Forest Naive Bayes. A coffee company wants to create a data set that includes mock up customer address information and the likelihood to churn. Which method is available to populate these fields? Bayesian Propensity Expression Import. U+ Bank has a chat bot to service its customers. When customers initiate a chat, they are asked to describe the issue they would like to resolve. U+ Bank wants to increase customer satisfaction by assigning the support agent from the correct department to help the customer. As a data scientist, you need to create a model which will predict the correct department based on the customer's input. To do this you build a_______________. Text categorization model Text extraction model Adaptive model Pega machine learning model. When selecting the list of predictors for an adaptive model you should consider a wide range of properties always use numeric type for integer properties select at least one date property select up to a maximum of 500 predictors. You are a company with a new and unique product, and you want to offer it to the right customer. Given the scenario, which rule type should you use? Predictive Model Scorecard Adaptive Model Decision Table. The decision components used on the strategy canvas can be individually configured Which function is available when configuring the Group By component? Divide True if Some Multiply Average. Inadecision strategy, in order to select the proposition with the highest propensity, you use a Priorities component, and sort propensity from highest to lowest Priorities component, and sort propensity from lowest to highest Switch component, and sort propensity from lowest to highest Switch component, and sort propensity from highest to lowest. When building a predictive model, the use of testing and validation samples _______________ increases the accuracy of models enables model validation in strategies is mandatory for segmentation validates the quality of input data. In Prediction Studio, the key metrics of adaptive models are visualized in a bubble chart. What three key metrics are displayed in this chart? (Choose Three) Number of responses Propensity of the model Success rate of the action Number of positive responses Number of active predictors Performance of the model. Which data is usually not appropriate to be used as a predictor? Customer zip code Historical interaction data Customer name Usage data. Lift is key metric for the performance of the adaptive models. To measure lift, you need a ____________ Standard model as a benchmark Control group with random actions Control group with a new action New adaptive model. |
Rapport de test