Example Process Flow Diagram

Task 12. Defining the Score Data Set

The purpose of predictive modeling is to apply the model to new data. If you are satisfied with the performance of the neural network model, then you can use this model to screen (score) the credit applicants. If you are not satisfied with this model, review the desired components of the sample, explore, modify, model, and assess methodology to try to obtain a better predictive model.

For this example, SAMPSIO.DMAGESCR is the name of the score data set. It is also stored in the sample library.

Follow these steps to set SAMPSIO.DMAGESCR as the score data set:

  1. Add a second Input Data Source node to the data mining workspace.

  2. Open the configuration interface to the Input Data Source node.

  3. Click the down arrow beside Role and select Score.

  4. Type SAMPSIO.DMAGESCR in the Source Data text box and press the ENTER key.

    [Data tab of Input Data Source window showing Source Data SAMPSIO.DMAGESCR source dat and SCORE Role.]

  5. Select the Variables tab. Notice that the target variable GOOD_BAD does not appear in this data set. You want to estimate the expected loss for the applicants by applying the scoring formula from the neural network model to this data set.

  6. Close the Input Data Source node and save changes.

space
space
Previous Page | Next Page | Top of Page

Copyright © 2006 by SAS Institute Inc., Cary, NC, USA. All rights reserved.