A shadow model runs alongside an active model. Both models receive production
data and generate outcomes, but the outcomes of the shadow model are not used to make
business decisions. Check how the shadow model performs over time, and if the model
proves better suited to your business needs, promote it as the active model.
Promoting shadow models is part of the Machine Learning Operations (MLOps) feature of
Before you begin: Review the performance of the shadow model. For more
information, see Monitoring predictions.
Result: The model is promoted for deployment to production as the
active model. For more information, see Understanding MLOps.
- In the navigation pane of Prediction Studio, click Predictions.
- From the list of predictions, open a prediction that contains a shadow model,
and then click the Models tab.
- Display the shadow model by expanding the twist arrow to the left of a current
- Ensure that the status of the model is
- To the right of the shadow model, click the More icon,
and then click Promote model.
- In the Promote model dialog box,
click Promote model to confirm.