Classification of Spam Data Using SVM-RFE

Support vector machine Recursive feature elimination (SVM-RFE) is investigated for feature selection from Spam E-mail Database. Features selected using SVM-RFE are classified using support vector machines. The proposed method outperforms existing methods in terms of classification accuracy, number of selected features and computational efficiency. The recursive feature elimination method reduces the feature space by removing some of the (non-relevant) features. Experimental results presented in this paper confirm the uses of the SVM-RFE for the analysis of Spam E-mail data. For the one data set, the overall performance measure increases from 75% to 93% with the proposed approach.