Experiments with Two Approaches for Tracking Drifting Concepts

Abstract

. This paper addresses the task of learning classifier from stream of labelled data. In this case we can face problem that the underling concepts can changes over time. The paper studies two mechanisms developed for dealing with changing concepts. Both are based on the time window idea. The first one forgets gradual, by assigning to the examples weight that gradually decreases over time. The second one uses a statistical test to detect changes in concept and then optimizes the size of time window, aiming to maximise the classification accuracy on the new examples. Both methods are general in nature and can be used with any learning algorithm. The objectives of the conducted experiments were to compare the mechanisms and explore whether they can combined to achieve a synergetic effect. Results from experiments with three basic learning algorithms (kNN, ID3 and NBC) using four datasets are reported and discussed.