Motius Glossary

The Motius Literary Index provides an alphabetical overview of the terms we use on our website.


Concept Drift

Concept Drift, also known as Data Drift or Model Drift, refers to the phenomenon in machine learning where the statistical properties of the target variable or the data distribution change over time. In other words, the relationships and patterns that the model learned during training become less accurate or even obsolete as new data becomes available.