Classifying Data Streams with Skewed Class Distribution and Concept Drifts

Classification is an important data analysis tool that uses a model built from historical data to predict class labels for new observations. More and more applications are featuring data streams, rather than finite stored data sets, which are a challenge for traditional classification algorithms. Concept drifts and skewed distributions, two common properties of data stream applications, make the task of learning in streams difficult. The authors aim to develop a new approach to classify skewed data streams that uses an ensemble of models to match the distribution over under-samples of negatives and repeated samples of positives.
Date: December 01, 2008
Book Title: IEEE Internet Computing (Special Issue on Data Stream Management), 12(6): 37-49, 2008
Type: InProceedings
Volume: 12
Number: 1089-7801
Pages: 37-49
Version: 2008-11-11
Publisher: IEEE
Downloads: 526

Has 1 soft copy


remote link

Bibtex


@InProceedings{Classifying_Data_Streams_with_Skewed_Cla,
  author = "Jing Gao and Bolin Ding and Wei Fan and Jiawei Han and Philip S Yu",
  title = "{Classifying Data Streams with Skewed Class Distribution and Concept Drifts}",
  month = "December",
  year = "2008",
  pages = "37-49",
  number = "1089-7801",
  volume = "12",
  booktitle = "IEEE Internet Computing (Special Issue on Data Stream Management), 12(6): 37-49, 2008",
  publisher = "IEEE",
}