A model governance team wants to ensure a model does not produce significantly different false positive rates across demographic groups before deployment. Where in SAS Model Manager governance is this addressed?
Select an answer to reveal the explanation.
Short Explanation
You need to look at the validation step because fairness means checking performance by demographic groups, not just overall scores. SAS Model Manager can put those group-level metrics into reporting output so you can spot bias before deployment.
Full Explanation
The model validation step with bias/fairness assessment using group-stratified performance metrics in reporting output is correct because fairness requires comparing performance across demographic groups, and validation reporting can show group-level metrics. The model comparison report comparing aggregate KPI metrics across model versions is wrong because it compares overall KPIs, not group-stratified metrics. The champion/challenger framework measuring aggregate KS statistics is wrong because it evaluates aggregate metrics. The model registration step where metadata tags indicate intended use is wrong because it records metadata but does not analyze bias.