English

edit
 
English Wikipedia has an article on:
Wikipedia

Etymology

edit

Concept refers to the hidden relationship between the inputs and outputs of the model.

Noun

edit

concept drift (countable and uncountable, plural concept drifts)

  1. (statistics, machine learning) The tendency of a statistical model to become less and less accurate over time in real-world conditions.
    • 2010, Mounia Lalmas et al., editors, Research and Advanced Technology for Digital Libraries [] , Springer, →ISBN, page 544:
      Regarding collection usage, frecency metrics are employed, combining frequency and recency, to effectively capture concept drift and temporal trends.
    • 2020, Zhiwen Yu et al., editors, Green, Pervasive, and Cloud Computing [] , Springer Nature, →ISBN, page 115:
      Concept drift is an important issue to be considered in data stream mining. In a real environment, the data distribution is constantly changing, and the model needs to be continuously updated to adapt to the new environment.