One of the challenges in inferring a classification model with good prediction accuracy is to select the relevant features that contribute to maximum predictive power. Many feature selection techniques have been proposed and studied in the past, but none so far claimed to be the best. In this paper, a novel and efficient feature selection method called Fuzzy Clustering Coefficients of Variation (FCCV) is proposed. FCCV is based on a very simple principle of variance-basis which finds an optimal balance between generalization and over-fitting. Through a computer simulation experiment, 44 datasets with substantially large number of features are tested by FCCV in comparison to four popular feature selection techniques. Results show that FCCV outperformed them in all aspects of averaged performances and speed. By the simplicity of design it is anticipated that FCCV will be a useful alternative of preprocessing method for classification especially with those datasets that are characterized by many features.