Gain-ratio-Based Selective classifiers for incomplete data
Jingnian Chen, Shujun Fu, Taorong Qiu · 2009
By deleting irrelevant or redundant attributes of a data set, selective classifiers can effectively improve the accuracy and efficiency of classification. Though many selective classifiers have been proposed, most of them deal with complete data. Yet actual data sets are often incomplete and have many redundant or irrelevant attributes. So constructing selective classifiers for incomplete data is important. With former work and information gain ratio, a hybrid selective classifier for incomplete data, denoted as GBSD, is presented. Experiment results on twelve benchmark incomplete data sets show that GBSD can effectively improve the accuracy and efficiency of classification while enormously reducing the number of attributes.