Skip to Main Content
The use of feature selection can improve accuracy, efficiency, applicability and understandability of a learning process and the resulting learner. For this reason, many methods of automatic feature selection have been developed. By using the modularization of feature selection process, this paper evaluates a wide spectrum of these methods and some additional ones created by combination of different search and measure modules. The evaluation identifies the most interesting methods and shows some recommendations about which feature selection method should be used under different conditions.