In SAS Model Manager, which term describes the automated process of detecting when a model's predictive performance has degraded enough to trigger an alert or retraining workflow?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — b is correct because model drift monitoring is the automated process of tracking performance metrics over time and detecting statistically significant degradation (concept drift or data drift) that triggers alerts or retraining. A (model validation) is a one-time evaluation step before deployment.
Full explanation below image
Full Explanation
B is correct because model drift monitoring is the automated process of tracking performance metrics over time and detecting statistically significant degradation (concept drift or data drift) that triggers alerts or retraining. A (model validation) is a one-time evaluation step before deployment. C (model versioning) is the process of tracking different iterations of a model in the registry. D (model packaging) is the process of bundling score code and resources for deployment.