Feature Selection in Imbalance data sets

Feature selection methods have been used these days in the various fields. Like information retrieval and filtering, text classification, risk management, web categorization, medical diagnosis and the detection of credit card fraud. In this paper we focus on feature selection for imbalanced problems. One of the greatest challenges in machine learning and data mining research is the class imbalance problems. Imbalance problems can appear in two different types of data sets: binary problems, where one of the two classes comprises considerably more samples than the other, and multiclass problems, where each class only contains a tiny fraction of the samples. In this paper we want to explain a prior knowledge for an expert system which can tell us which feature selection metrics perform best based on our data characteristics and regardless of the classifier used.