Model Drift & Model Robustness Simulations

From The Foundation for Best Practices in Machine Learning
Technical Best Practices > Performance Robustness > Model Drift & Model Robustness Simulations
Jump to navigation Jump to search

Model Drift & Model Robustness Simulations[edit]

Control

Document and perform simulations of Model training and retraining cycles, using historic and synthetic data. Document and assess the effects of temporal changes to, amongst other things, the Selection Function, Data Generating Process and Data Drift on the drift in performance and error distributions of said simulations. If Model drift is apparent, document and perform further simulations for Model drift response optimization, and/or consider refining Product Definitions.


Aim

To (a) assess and control for Model propensity for Model drift; (b) determine the robustness of Model performance as a function of data changes; (c) determine appropriate Product response to drift; and (d) highlight associated risks that might occur in the Product Lifecycle.


Additional Information[edit]