A survey on feature ranking by means of evolutionary computation

The paper presents a review of current evolutionary algorithms for feature ranking in data mining tasks involving automated learning. This issue is highly important as real-world problems commonly suffer from the curse of dimensionality. By weighting the significance of each attribute from a data set, the less influential indicators can be disposed of before learning actually takes place, making the task become easier and less noisy. Moreover, for several practical domains of application, such as medicine for instance, a ranking of the most indicative attributes for a diagnosis are as vital as the computational learning support for the final decision taking. Evolutionary algorithms are one of the most frequently used heuristics for a diverse range of tasks, due to their simple and flexible nature. Therefore, the current study investigates the numerous recent trends in employing the evolutionary computation field for the subject of feature ranking. 2010 Mathematics Subject Classification. Primary 68T20; Secondary 68T10.