On reducing classifier granularity in mining concept-drifting data streams

@article{Wang2005OnRC,
  title={On reducing classifier granularity in mining concept-drifting data streams},
  author={Peng Wang and Haixun Wang and Xiaochen Wu and Wei Wang and Baile Shi},
  journal={Fifth IEEE International Conference on Data Mining (ICDM'05)},
  year={2005},
  pages={8 pp.-}
}
Many applications use classification models on streaming data to detect actionable alerts. Due to concept drifts in the underlying data, how to maintain a model's up-to-dateness has become one of the most challenging tasks in mining data streams. State of the art approaches, including both the incrementally updated classifiers and the ensemble classifiers, have proved that model update is a very costly process. In this paper, we introduce the concept of model granularity. We show that reducing… CONTINUE READING
Highly Cited
This paper has 18 citations. REVIEW CITATIONS