Concept drift Machine Learning
noun
Definition: A change over time in the statistical properties of the target variable or data distribution that degrades model performance [Bakanach 2023/2024].
Example in context: “However, it is known that real-world conditions are characterized by issues such as concept drift that limit the generalizability of supervised approaches (Lu et al., 2018).” [Fagni, Cresci 2022]
Related terms: data drift, online learning, model monitoring