Overview of the Score Code Export Node

Users of SAS Enterprise Miner develop data mining models that use measured attributes to either characterize or predict the value of an event. These models are developed on historical data where an event has been measured or inferred. The models are then applied to new data for which the attributes are known, but the event has not yet occurred. For example, a model can be created based on a credit institution’s records of payments that customers made and missed last year. Then the model can be used to predict which customers will miss payments this year.

SAS Enterprise Miner creates SAS language score code for the purpose of scoring new data. Users run this code in production systems to make business decisions for each record of new data.

The Score Code Export node is an extension for SAS Enterprise Miner that exports files that are necessary for score code deployment. Extensions are programmable add-ins for the SAS Enterprise Miner environment.

The following icon is the Score Code Export node as it appears in a SAS Enterprise Miner process flow diagram.

The following files are exported by the Score Code Export node:

the SAS scoring model program (score.sas).
a properties file that contains a description of the variables that are used and created by the score code (score.xml).
if the scoring program contains user-defined formats, a format catalog.
an XML file containing descriptions of the final variables that are created by the score code. This file can be kept for decision-making processes.
a ten-row sample of the scored data set showing typical cases of the input attributes, intermediate variables, and final output variables used to develop the score code. This data set can be used to test and debug new scoring processes.
a ten-row sample table of the training data set showing the typical cases of the input attributes used to develop the score code.

For more information about the exported files, see Output Files. For more information about using SAS Enterprise Miner, see the SAS Enterprise Miner Help.