Predictive Analytics Modeler Explorer Award | Complete Questions & Verified Answers for Exam Success

Predictive Analytics Modeler Explorer
Award | Complete Questions & Verified
Answers for Exam Success

Which statement describes the goal of a typical data mining project?
j j j j j j j j j j




A. Produce reports describing customer behavior, based on empirical data. j j j j j j j j




B. Assess risk associated with past business decisions. j j j j j j




C. Predict the behavior of future cases based on past information. j j j j j j j j j




D. Provide insightful financial reports that help business decision making. j j j j j j j j j Answer- C. j j




Predict the behavior of future cases based on past information
j j j j j j j j j




Which tab allows you to count how many valid records exist in the data audit node dialog?
j j j j j j j j j j j j j j j j




A. Annotations
B. Output
C. Settings
D. Quality Answer- D. Quality j j j j




You need to create a single report that can be run at different times for different months
j j j j j j j j j j j j j j j j j




without editing the stream after it has been deployed. How should you build the stream?
j j j j j j j j j j j j j j




A. Make a filler node to put the correct value into the stream.
j j j j j j j j j j j




B. Create a session parameter for the month. Enter the data as needed.
j j j j j j j j j j j




C. Hard code the month in a SuperNode. Update when necessary.
j j j j j j j j j




D. Use a partition node to create separate sample groups for each month. Answer- B.
j j j j j j j j j j j j j j




Create a session parameter for the month. Enter the data as needed.
j j j j j j j j j j j




What is a segmentation modeling method that automatically sets the number of clusters into
j j j j j j j j j j j j j j




which records are then classified?
j j j j




A. Kohonen networks j




B. AutoCluster
C. TwoStep
D. K-Means Answer- C. TwoStep j j j j




Identify an important characteristic of the segmentation model.
j j j j j j j




A. The segmentation model identifies clusters in the data.
j j j j j j j




B. The segmentation model does not create a nugget.
j j j j j j j




C. The segmentation model has multiple targets.
j j j j j

,D. The segmentation model has a predefined output.j j j j j j j Answer- A. The segmentation j j j j




model identifies clusters in the data.j j j j j




You are building a stream with SPSS MODELER. The bottom of the Table output
j j j j j j j j j j j j j j




window shows many records with all $null$ values. How can you eliminate these
j j j j j j j j j j j j j




records from your model? j j j




A. Edit the properties of the stream and choose the option: "Exclude null values".
j j j j j j j j j j j j




B. Generate a Select node where data_known="yes". j j j j j




C. Edit the Table node and choose the option: "Exclude null values".
j j j j j j j j j j




D. Edit the Select node and add "where data_known="yes" to the SQL statement.
j j j j j j j j j j j j




Answer- B. Generate a Select node where data_known="yes". j j j j j j j




How do you specify which records are grouped together in a derive node in count mode?
j j j j j j j j j j j j j j j




A. by entering a 'Reset when' criteria
j j j j j




B. by entering an 'Increment by' of 0
j j j j j j




C. by entering an 'Initial value' of the field name
j j j j j j j j




D. by entering the 'Group by' field Answer- A. by entering a 'Reset when' criteria
j j j j j j j j j j j j j j




You have built a stream in SPSS MODELER that includes two source nodes and four output
j j j j j j j j j j j j j j j j




nodes. How can you run the stream to produce all four outputs?
j j j j j j j j j j j




A. Click the Run button from the main menu. j j j j j j j




B. Right-click a source node and choose Run "Selection". j j j j j j j




C. Right-click one of the terminal nodes and choose Run All". j j j j j j j j j




D. Select a source node and click the Run button from the main menu. Answer- A. j j j j j j j j j j j j j j j




Click the Run button from the main menu.
j j j j j j j




Which selection is indicative of a Association modeling objective?
j j j j j j j j




A. A person's age is a determining factor to predict whether a Website visitor will click on an
j j j j j j j j j j j j j j j j j




ad for something interesting on Facebook.
j j j j j




B. Subjects who change jobs every six months are more likely to default on an j j j j j j j j j j j j j j




automobile loan. j




C. Income is a determining factor for whether a family takes a summer vacation to a j j j j j j j j j j j j j j j




foreign country or resort area. j j j j




D. Cell phone users who subscribe to plan A will likely purchase the newest cell phone as
j j j j j j j j j j j j j j j j




soon as it is released. Answer- D. Cell phone users who subscribe to plan A will likely
j j j j j j j j j j j j j j j j j




purchase the newest cell phone as soon as it is released. j j j j j j j j j j




Which of the following means a model can fit the training set perfectly and fails with unseen
j j j j j j j j j j j j j j j j j




future data? j




A. Underfitting
B. Prediction
C. Overfitting
D. Cross validation Answer- C. Overfitting j j j j j

, You are using Data Refinery, which tab can give you insights into your data, helping you
j j j j j j j j j j j j j j j j




identify patterns, connections, and relationships?
j j j j




A. Functions
B. Profile
C. Operations
D. Visualizations Answer- D. Visualizations j j j j




Which node will create a classification table, based on the accuracy of a model?
j j j j j j j j j j j j j




A. Sample
B. Analysis
C. Partition
D. Data Audit Answer- B. Analysis j j j j j




Your Data Set consists of 5000 records describing houses and you are trying to predict the
j j j j j j j j j j j j j j j j




house price, if one of the fields in your data set describes the area of the house, what should
j j j j j j j j j j j j j j j j j j j




the role of this field be?
j j j j j




A. Both
B. Partition
C. Target
D. Input Answer- D. Input j j




Which statement describes a CHAID analysis?
j j j j j




A. the process of Detecting Automatic Interaction through classification and heuristics
j j j j j j j j j




B. a classification and prediction method based on classification and regression
j j j j j j j j j




C. a decision-tree technique that looks for predictive variables based on Chi-square
j j j j j j j j j j j




testing
D. a modified Chi-square analysis that produces a predictive decision tree Answer- C. a
j j j j j j j j j j j j j




decision-tree technique that looks for predictive variables based on Chi-square testing j j j j j j j j j j




Which of the following can't be a reason for a data mining project failure?
j j j j j j j j j j j j j




A. Not enough time spent on data preparation
j j j j j j




B. The complexity of the model is of O(n2)
j j j j j j j




C. Bad quality data j j




D. Some inputs/factors can't be legally used Answer- B. The complexity of the model is of
j j j j j j j j j j j j j j j




O(n2)

Which of the following means a machine learning model cannot fit the training data or
j j j j j j j j j j j j j j j




generalize to new data? j j j




A. Overfitting
B. Feedforwad
C. Underfitting
D. Backpropagation Answer- C. Underfitting j j j j




Which statement is true about Apache Spark?
j j j j j j




A. Apache Spark is a service with features for training and deploying machine learning
j j j j j j j j j j j j j




models and neural networks. j j j