Model-based explanations of concept drift

Abstract

Concept drift refers to the phenomenon that the distribution generating the observed data changes over time. If drift is present, machine learning models can become inaccurate and need adjustment. While there do exist methods to detect concept drift or to adjust models in the presence of observed drift, the question of explaining drift, i.e., describing the potentially complex and high dimensional change of distributions in a human-understandable fashion, has hardly been considered so far. This problem is of importance since it enables an inspection of the most prominent characteristics of how and where drift manifests. Hence, it allows human understanding of the change and it increases acceptance of life-long learning models. In this paper, we present a novel technology characterizing concept drift in terms of the characteristic change of spatial features based on various explanation techniques. To do so, we propose a methodology to reduce the explanation of concept drift to an explanation of models that are trained in a suitable way to extract relevant information from the drift. This way, a large variety of explanation schemes is available, and a suitable method can be selected for the problem at hand. We outline the potential of this approach and demonstrate its usefulness in several examples.