Genetic Programming based Feature Construction for Classification with Incomplete Data

Missing values are an unavoidable problem in many real-world datasets. Dealing with incomplete data is an crucial requirement for classification because inadequate treatment of missing values often causes large classification error. Feature construction has been successfully applied to improve classification with complete data, but it has been seldom applied to incomplete data. Genetic programming-based multiple feature construction (GPMFC) is a current encouraging feature construction method which uses genetic programming to evolve new multiple features from original features for classification tasks. GPMFC can improve the accuracy, and reduce the complexity of many decision trees and rule-based classifiers; however, it cannot directly work with incomplete data. This paper proposes IGPMFC which is extended from GPMFC to tackle with incomplete data. IGPMFC uses genetic programming with interval functions to directly evolve multiple features for classification with incomplete data. Experimental results reveal that not only IGPMFC can substantially improve the accuracy, but also can reduce the complexity of learnt classifiers facing with incomplete data.