Predictions refer to the output of a model after it has been trained. The ModelOps UI provides a view of the predictions of a dataset and a distribution plot for its values.
Prediction drift is specific to monitoring the data statistics of the model output. You can monitor whether model predictions are suddenly deviated from what they normally predict.
The Prediction stats area displays the following details.
Property | Description |
---|---|
Name | Specifies the name of the prediction. |
Group | Specifies the group the prediction belongs to. |
Type | Specifies the data type of prediction as Continuous or Categorical depending on the type of problem being solved. |
PSI drift value | Specifies changes in the distribution of a variable over time to detect model performance issues. |
- Select a prediction in the Prediction stats area. The right section of the page displays the Targets distribution plot for the selected prediction. It displays the prediction categories on the x-axis and probability on the y-axis.