Basel II Reports :: SAS(R) Model Manager 12.1: User's Guide

About Basel II Reports

Basel II reports in SAS Model Manager provide several statistical measures and tests to validate the stability, performance, and calibration using Loss Given Default (LGD) and Probability of Default (PD) models.

Model stability measures

The model stability measures track the change in distribution of the modeling data and the scoring data.

Model performance measures

The model performance measures report this information:

The model’s ability to discriminate accounts that have defaulted with those that have not defaulted. The score difference between the accounts that default and those that do not helps determine the cut-off score, which is used to predict whether a credit exposure is a default.
The relationship between the actual default probability and the predicted probability. This information is used to understand a model’s performance over a period of time.

Model calibration measures

The model calibration measures check the accuracy of the LGD and PD models by comparing the correct quantification of the risk components with the available standards.

For a description of the statistical measures, see Statistical Measures Used in Basel II Reports.

The Loss Given Default and Probability of Default Report Properties

In order to create the Basel II reports, SAS Model Manager must know the input and output variables for the model. To run the reports, the New Report window requires the name of an input table. The input table can contain only input variables, or it can contain input and output variables. If the input table contain only input variables only, a scoring task must be run to obtain the output variable. If the input table contains the input and output variables, no scoring is necessary. You specify whether a scoring task must be run by setting the Run Scoring Task property in the New Report window. If the input table contains the input and output variables, the value of the Run Scoring Task can be No. If the input table contains only input variables, the Run Scoring Task property must be set to Yes.

The New Report window report properties requires the name of the variables from the input and output tables in order to map these variables to variables that are used by SAS Model Manager uses to create the reports.

The LGD report properties map these variables:

Time Period Variable	specifies the variable that is used to indicate a time period. The first time period begins with 1 and typically increments by 1. The default is period.
Time Label Variable	(optional) specifies a label for the time period. If this variable exists in the input table, the report output contains a table that maps time periods to time labels.
Actual Variable	specifies the actual LGD variable. The default is lgd.
Predicted Variable	specifies the output prediction variable that is used only if scoring for the report is not performed by SAS Model Manager. If the report scoring is done by SAS Model Manager, this variable should be excluded by the input data set. The default is p_lgd.
Pool Variable	specifies the variable that names pool IDs. The default is pool_id.

The PD report properties map these variables:

Time Period Variable	specifies the variable that is used to indicate a time period. The first time period begins with 1 and typically increments by 1. The default is period.
Time Label Variable	(optional) specifies a label for the time period. If this variable exists in the input table, the report output contains a table that maps time periods to time labels.
Scorecard Bin Variable	specifies the scoring output variable that names the scorecard bins. The input table must include this variable if scoring for the PD report is performed outside of SAS Model Manager. If scoring is done by SAS Model Manager, do not include this variable in the input data set. The default is scorecard_bin.
Scorecard Points Variable	specifies the scoring output variable that names the scorecard points. The input table must include this variable if scoring for the PD report is performed outside of SAS Model Manager. If scoring is done by SAS Model Manager, do not include this variable in the input data set. The default is scorecard_points.
Cut-off Value	specifies the variable that is used to derive whether a credit exposure is a default. The cut-off value is also used to compute accuracy, sensitivity, specificity, precision, and error rate measures. You can use the score difference between accounts that default on loans and those that do not default on loans to determine the cut-off value. The default is 100.

Create a Loss Given Default Report

To create an LGD report, follow these steps:

Expand the version folder .
Right-click the Reports node and select ReportsNew Report. The New Report window appears.
Select Loss Given Default Report from the Type box.
In the Format box, select the type of output that you want to create. The default is PDF. The other option is RTF.
In the Select Models box, select the box for the model that you want to report on.
Complete the Report Properties, the properties with an asterisk are required:
- Enter a report name if you do not want to use the default value for the Name property.
- (Optional) Enter a report description.
- For the Input Table property, click the Browse button and select a table from the SAS Metadata Repository tab or from the SAS Libraries tab that is used for scoring during the creation of the LGD report. The table can contain only input variables or it can contain input and output variables.
- If the input table that is specified in the Input Table property contains only input variables, set Run Scoring Task to Yes. If the input table contains input and output variables, set Run Scoring Task to No.
- The Time Period Variable specifies the variable from the input table whose value is a number that represents the development period. This value is numeric. The default is period.
- (Optional) In the Time Label Variable field, enter the variable from the input table that is used for time period labels. When you specify the time label variable, the report appendix shows the mapping of the time period to the time label.
- Actual Variable is the actual LGD variable. The default is lgd.
- Predicted Variable is the project scoring output variable. If the scoring for the LGD report is performed outside SAS Model Manager, the input data set must include this variable. If the scoring for the LGD report is done by SAS Model Manager, the input data set should not include this variable. The default is p_lgd.
- Pool Variable is the variable from the input table that is used to identify a two-character pool identifier. The default is pool_id.
Note: The variable names that you specify can be user-defined variables. A variable mapping feature maps the user-defined variables to required variables.
Click OK. A dialog box message confirms that the report was created successfully.

Create a Probability of Default Report

To create a PD report, follow these steps:

Expand the version folder .
Right-click the Reports node and select ReportsNew Report. The New Report window appears.
Select Probability of Default Model Validation Report from the Type box.
In the Format box, select the type of output that you want to create. The default is PDF. The other option is RTF.
In the Select Models box, select the box for the model that you want to report on.
Complete the Report Properties:
- Enter a report name if you do not want to use the default value for the Name property.
- (Optional) Enter a report description.
- For the Input Table property, click the Browse button and select a table from the SAS Metadata Repository tab or from the SAS Libraries tab. The table can contain only input variables or it can contain input and output variables.
- If the input table that contains only input variables, set Run Scoring Task to Yes. If the input table contains input and output variables, set Run Scoring Task to No.
- The Time Period Variable specifies the variable from the input table whose value is a number that represent the development period. This value is numeric. The time period for PD reports begin with 1. The default is period.
- (Optional) In the Time Label Variable field, enter the variable from the input table that is used for time period labels. When you specify the time label variable, the report appendix shows the mapping of the time period to the time label.
- Scorecard Bin Variable is the variable from the input table that contains the scorecard bins. If the scoring job for the PD report is run outside SAS Model Manager, the scorecard bin variable must be a variable in the input table. If scoring is done within SAS Model Manager, do not include the variable in the input table. The default is scorecard_bin.
- Scorecard Points Variable is the variable that contains the scorecard points. If the scoring job for the PD report is run outside SAS Model Manager, the scorecard points variable must be a variable in the input table. If scoring is done within SAS Model Manager, do not include the variable in the input table. The default is scorecard_points.
- Cut-off Value is the maximum value that can be used to derive the predicted event and to further compute accuracy, sensitivity, specificity, precision, and error rate. The default is 100.
Note: The variable names that you specify can be user-defined variables. A variable mapping feature maps the user-defined variables to required variables.
Click OK. A dialog box message confirms that the report was created successfully.

Basel II Reports

About Basel II Reports

The Loss Given Default and Probability of Default Report Properties

Create a Loss Given Default Report

See Also

Create a Probability of Default Report

See Also