Number of questions: 25
Time allowed in minutes: 60
Required passing score: 64%
Languages: English, Japanese
Business Understanding (8%)
Review of the CRISP methodology
General Operations in Modeler (20%)
Reading different types of files into Modeler
Data Understanding (20%)
Extent of missing data
Field distribution and summary statistics
Auto-checking for missing or out-of-bounds data
Looking at bivariate relationships between variables
Data Preparation (28%)
Automated data preparation
Creating new variables with the Derive Node
Creating new variables with the Reclassify Node
Combining data files
Missing value replacement
Scoring new data with a deployed model
Exporting model results
IBM Certified Associate – SPSS Modeler Data Mining v2
Job Role Description / Target Audience
This certification is designed for Business Partners with a beginning knowledge of IBM IBM SPSS Modeler version 14 or higher working in government, academia, or business who use the IBM SPSS Modeler product to perform data mining activities including data preparation, data understanding, and modeling.
The IBM Certified Associate – SPSS Modeler Data Mining v2 may utilize the IBM SPSS Modeler product for applications such as fraud detection, customer management and churn, risk management, and so forth.
True or false: the optimal binning method in the Binning node uses a Supervisor field to determine the binning cut points.
How many phases are in the CRISP-DM Process Methodology?
True or false: association models require all fields used to be defined with the role of both.
Which of the following types of nodes will have data flowing both in and out, when used in a stream?
A. Record Ops