Feature Selection and the Chessboard Problem

Abstract

Feature selection methods are usually classified into three groups: filters, wrappers and embedded methods. The second important criterion of their classification is an individual or multivariate approach to evaluation of the feature relevance. The chessboard problem is an illustrative example, where two variables which have no individual influence on the dependent variable can be essential to separate the classes. The classifiers which deal well with such data structure are sensitive to irrelevant variables. The generalization error increases with the number of noisy variables. W e discuss the feature selection methods in the context of chessboard-like structure in the data with numerous irrelevant variables.