A data stream can be considered as a sequence of examples that arrive continuously and are potentially unbounded, such as web page visits, sensor readings and call records. One of the serious and challenging problems that appears in a data stream is concept drift. This problem occurs when the relation between the input data and the target variable changes over time. Most existing works make an optimistic assumption that all incoming data are labelled and the class labels are available immediately. However, such an assumption is not always valid. Therefore, a lack of class labels aggravates the problem of concept drift detection. With this motivation, we propose a drift detector that reacts naturally to sudden drifts in the absence of class labels. In a novel way, the proposed detector reacts to concept drift in the absence of class labels, where the true label of an example is not necessary. Instead of monitoring the error estimates, the proposed detector monitors the diversity of a pair of classifiers, where the true label of an example is not necessary to determine whether components disagree. Using several datasets, an experimental evaluation and comparison is conducted against several existing detectors. The experiment results show that the proposed detector can detect drifts with less delay, runtime and memory usage.
This is an open access article distributed under the Creative Commons Attribution License
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited