Learning Concept Drift Using Adaptive Training Set Formation Strategy

We live in a dynamic world, where changes are a part of everyday life. When there is a shift in data, the classification or prediction models need to be adaptive to the changes. In data mining the phenomenon of change in data distribution over time is known as concept drift. In this research, the authors propose an adaptive supervised learning with delayed labeling methodology. As a part of this methodology, the atuhors introduce Adaptive Training Set Formation for Delayed Labeling Algorithm (SFDL), which is based on selective training set formation. Our proposed solution is considered as the first systematic training set formation approach which takes into account delayed labeling problem. It can be used with any base classifier without the need to change the implementation or setting of this classifier. The authors test their algorithm implementation using synthetic and real dataset from various domains which might have different drift types (sudden, gradual, incremental recurrences) with different speed of change. The experimental results confirm improvement in classification accuracy as compared to ordinary classifier for all drift types. The authors’ approach is able to increase the classifications accuracy with 20% in average and 56% in the best cases of our experimentations and it has not been worse than the ordinary classifiers in any case. Finally a comparison with other four related methods to deal with changing in user interest over time and handle recurrence drift is performed. These methods are simple incremental method, time window approach with different window size, instance weighting method and conceptual clustering and prediction framework (CCP). Results indicate the effectiveness of the proposed method over other methods in terms of classification accuracy.