Prequential AUC for Classifier Evaluation and Drift Detection in Evolving Data Streams.
Dariusz BrzezinskiJerzy StefanowskiPublished in: NFMCP (2014)
Keyphrases
- evolving data streams
- concept drift
- drift detection
- classification algorithm
- streaming data
- data streams
- decision trees
- feature selection
- learning algorithm
- training set
- support vector machine
- training data
- logistic regression
- non stationary
- class labels
- random forests
- naive bayes
- stream data
- stream mining
- training examples
- feature space
- support vector
- data stream mining
- image processing
- training samples