Drift Tab offers a deep dive into Prediction Drift, Feature Drift, and Data Distribution Change.
Your model's prediction drift monitor goes off! How do you troubleshoot what is causing your outputs to drift?
Accessing Drift Tab
You can access the Drift Tab of a particular model by navigating to the model under Models, then click the Drift from the options including Monitors and Dashboards.
Prediction Drift refers to change in the predictiondistribution, generated by your model. Arize can surface change in distributions for all model types and problems: Regression, Binary/Multi Classification, and Score Model.
Guide: Visualizing Prediction Drift (in PSI) and Distribution Comparison
By clicking on specific points of the Prediction Drift curve, Arize also surfaces change in Distribution Comparison and Feature Drift! Allowing you to narrow down on issues to troubleshoot your model.
Feature Drifts refer to changes in your feature distribution. They are relatively common in the real world, can happen at any time in production, and you may not know if it would impact your model!
Arize allows you to analyze any situations pertinent to your model. You can sort in any of the columns to deep drive into explaining your model performance.
Prediction Drift Impact can surface when drift has impacted your model. Drift (PSI) is a measurement of how much your distribution has drifted. Lastly, Feature Importance helps your explain why even small Drift (PSI) can have significant Drift Impact.
Guide: Clicking on PSI to Closely Monitor Drift Impact