Data Drift Detection

From The Foundation for Best Practices in Machine Learning

Data Drift Detection

Control

Define and deploy monitoring metrics and thresholds for detecting sudden and/or gradual, short term and/or long term changes in data distributions, giving priority to those that can detect past observed changes. (See Section 12.2.1. - Missing and Bad Data Handling for further information). Document and assess distribution families, statistical moments, similarity measures, trends and seasonalities.


Aim

To (a) prevent predictions from diverging from training data and/or Product Definitions by assessing whether production data is representative of older data; and (b) highlight associated risks that might occur in the Product Lifecycle.


Additional Information