In predictive analytics and machine learning, the concept drift means that the statistical properties of the target variable, which the model is trying to predict, change over time in unforeseen ways. This causes problems because the predictions become less accurate as time passes.
The term concept refers to the quantity to be predicted. More generally, it can also refer to other phenomena of interest besides the target concept, such as an input, but, in the context of concept drift, the term commonly refers to the target variable.
Read more about Concept Drift: Examples, Possible Remedies, Software, Projects, Meetings, Mailing List, Bibliographic References
Famous quotes containing the words concept and/or drift:
“the full analysis of the notions of saying something and understanding what one said inevitably involves a concept which, as I will show in detail, essentially corresponds to the Cartesian idea of thought.”
—Zeno Vendler (b. 1921)
“To drift with every passion till my soul
Is a stringed lute on which all winds can play,
Is it for this that I have given away
Mine ancient wisdom, and austere control?
Methinks my life is a twice-written scroll
Scrawled over on some boyish holiday”
—Oscar Wilde (1854–1900)