Exploring an iterative feature selection technique for highly imbalanced data sets.
Taghi M. KhoshgoftaarKehan GaoAmri NapolitanoPublished in: IRI (2012)
Keyphrases
- highly imbalanced
- feature selection
- data sets
- class distribution
- imbalanced data
- cost sensitive
- feature selection algorithms
- class imbalance
- text classification
- text categorization
- multi class
- training data
- support vector machine
- test set
- high dimensionality
- support vector
- machine learning
- test data
- ensemble classifier
- feature space
- data streams
- linear regression
- decision trees
- cost sensitive learning
- semi supervised
- naive bayes
- unsupervised learning
- dimensionality reduction