A model registry in SAS Model Manager contains version 1 (champion) and version 2 (challenger) of a credit risk model. Version 2 shows a Gini coefficient of 0.71 vs. 0.64 for version 1 in the challenger test. What action should the data scientist recommend?
Select an answer to reveal the explanation.
Short Explanation
You promote the challenger with the higher Gini, but only after validation, documentation, and stakeholder approval. The current champion's production history doesn't beat the clear 7-point Gini gain.
Full Explanation
Promote the challenger model with the higher Gini after completing validation, documentation, and stakeholder approval. The challenger shows superior discriminatory performance, Gini 0.71 versus 0.64, so in SAS Model Manager the next step is formal validation, model documentation, and approval before champion promotion. Keeping the current champion because it was validated in production ignores the clear improvement. Archiving both and training version 3 for Gini above 0.80 is premature; the 7-point Gini gain is substantial and warrants promotion, not abandonment. Deploying both models with the permanent 50/50 traffic split is not the champion/challenger strategy and would keep using the inferior model for half of production decisions.