The Scorecard Builder algorithm produces General Additive Models (GAM) using linear regression splines.
It is called the Scorecard Builder as these models can be used for traditional risk scorecards and can be calibrated so that a score has a specific meaning.
This algorithm should always be more accurate than logistic regression and does not require that the data be 'pre-processed' in order to account for any non-monotonic variables.
The data selection tabs in the Scorecard Builder are the same as in the Logistic Regression module.
See,
Accessing Module
Defining Data
Categorical Variables
