Learning in the presence of concept drift and hidden contexts

Gerhard Widmer, Miroslav Kubat

Research output: Contribution to journalArticlepeer-review

1121 Scopus citations

Abstract

On-line learning in domains where the target concept depends on some hidden context poses serious problems. A changing context can induce changes in the target concepts, producing what is known as concept drift. We describe a family of learning algorithms that flexibly react to concept drift and can take advantage of situations where contexts reappear. The general approach underlying all these algorithms consists of (1) keeping only a window of currently trusted examples and hypotheses; (2) storing concept descriptions and reusing them when a previous context re-appears; and (3) controlling both of these functions by a heuristic that constantly monitors the system's behavior. The paper reports on experiments that test the systems' performance under various conditions such different levels of noise and different extent and rate of concept drift.

Original languageEnglish (US)
Pages (from-to)69-101
Number of pages33
JournalMachine Learning
Volume23
Issue number1
DOIs
StatePublished - Apr 1996
Externally publishedYes

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Learning in the presence of concept drift and hidden contexts'. Together they form a unique fingerprint.

Cite this