A shadow model runs in your production environment alongside an active model. The
shadow model receives production data and generates outcomes, but does not impact your
business decisions. The system tracks the outcomes to help you evaluate how the shadow
model performs in production. If the model is not suitable for your needs, you can
reject the model, and then replace it with a different one.
Rejecting 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 shadow model is removed. You can replace the currently
active model with a new candidate model. For more information, see Replacing models in predictions with 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 the
- Ensure that the status of the model is
- To the right of the shadow model, click the More icon,
and then click Reject model.
- In the Reject model dialog box, click
Reject model to confirm.