Directly evolving classifiers for missing data using genetic programming
Cao Truong Tran, Mengjie Zhang, Peter M. Andreae · 2016
Missing values are a common issue in many industrial and real-world datasets. Coping with datasets containing missing values is an important requirement for classification because inadequate treatment of missing values may result in large errors on classification. Genetic programming (GP) has been successfully used to evolve classifiers, but it has been applied mainly to complete data. This paper proposes IGP, a GP method for directly evolving classifiers for missing data. In order to directly evolve classifiers for missing data, IGP uses interval functions as the GP function set and builds a set of classifiers for each classification problem. Experiments on 10 benchmark datasets compared IGP with five other classifiers on classification performance. Experimental results showed that, in most cases, IGP achieves significantly better classification accuracy than the other methods.