Define variable cutpoints
Categorization based on cutpoints is a type of data transformation. If the source data for the data configuration does not contain a variable that categorizes values in a way that is needed for stratification or subsetting during a data mining run, you can create categories by defining cutpoints for the variable. You can define categories for only a continuous variable; that is, numeric or date variables.
For example, the source data contains Age, but not Age Group. The data miner wants to subset data by the following groups: 18 or younger, 19-65, and over 65. You can define a variable based on Age, and then categorize those age values into groups by specifying cutpoint values that indicate the range of each category.
Parent topic: Transform data