Monitoring Performance of a Model without Score Code

If you want to monitor the performance of a model for which you no longer have the score code, you can import a model without SAS score code. If the performance data set contains the predicted values, the score.sas file can be empty.
To monitor the performance of a model without score code:
  1. Prepare the following model files:
    • XML file that defines the model input variables (inputvar.xml)
    • XML file that defines the model output variables (outputvar.xml)
    • XML file that defines the model target variables (targetvar.xml)
    • empty SAS score code file (score.sas)
  2. Select Modelsthen selectProjects
  3. Create a project that has a model function type of Classification or Prediction. You can skip this step if you have already created a project.
  4. Open a project and verify that the project properties are set.
    1. If it is a project that has a model function property value of Classification, verify that the following project properties are set:
      • Training target variable (for example, bad)
      • Target event value (for example, 1)
      • Class target level as Binary
      • Output event probability variable (for example, score)
    2. If it is a project that has a model function property value of Prediction, verify that the following project properties are set:
      • Training target variable (for example, lgd)
      • Class target level as Interval
      • Output prediction variable (for example, p_lgd)
  5. Select the Models page.
  6. Click Import model from and select from local files.
    Note: If the model already exists, you can open a model to add model files to an existing model. For more information, see Add Model Files to an Existing Model.
  7. Navigate to the folder on your computer that contains the component files for your model.
  8. Select a classification or prediction template from the Choose a model template list.
  9. Enter a text value in the model Name field.
  10. Click Properties and specify the model properties.
  11. Click Files and select the local files from the SAS Workspace Server that match the template files. You cannot delete a file after you have added it. To replace the file, select another file or cancel the import and start over. The following files are required:
    • inputvar.xml
    • outputvar.xml
    • targetvar.xml
    • score.sas
    Note: The filenames that you created for the model do not have to match the template filenames. However, the file contents must meet the file property requirements. For more information, see Model Template Component Files or Model Template Component Files.
  12. Click OK.
  13. Open the model, and set the model-specific properties. The value for the Score code type property must be set to DATA step.
  14. Expand Variables and select Output Mapping in order to set the output variable mappings for the model. Select a value for each variable and click Save.
  15. Click Close to close the model.
  16. Select the model and click Set as champion model to set as the champion model. For more information, see Ensure That Champion and Challenger Models Are Set.
  17. Before defining performance, verify that the performance data set is registered in the SAS Metadata Repository and is available in the Data category view. Make sure that the data set contains the following variables:
    • model input variables
      Note: You must have the variable columns in the table, but the values can be missing.
    • target variable
    • prediction variables
    • variables for characteristic analysis
  18. Edit a project’s performance definition on the Performance page. Specify the performance data set that contains the predicted values. Also, be sure to clear the Run model score code option for the Data Processing Method section of the Edit Performance Definition wizard. For more information, see Edit and Execute a Performance Definition.
Last updated: February 22, 2017