SETL: a transfer learning based dynamic ensemble classifier for concept drift detection in streaming data

Concept drift is one of the most prominent issues in streaming data that machine learning models need to address. Most of the research in the field of concept drift targets updating the prediction model for recovery from concept drift. A little effort has been put into the development of a learning system that can learn drifting concepts with minimal overhead. In this paper, a dynamic ensemble classifier is designed to detect and adapt the concept drifts in streaming data. Thereupon, a novel approach- Selective Ensemble using Transfer Learning (SETL) is proposed that has the ability to adapt the new concept of data. It employs a transfer learning and a weighted majority voting scheme to enable resource optimization. It also overcomes the issues, such as negative transfer and overfitting that may occur during the process of transfer learning. The experiments are performed using real-world open-source datasets. The results indicate that SETL outperforms existing state-of-the-art algorithms for most of the datasets in terms of performance metrics such as Accuracy, F1-score, Kappa measure, precision and recall.