Parameter determination and feature selection for C4.5 algorithm using scatter search approach

摘要: The C4.5 decision tree (DT) can be applied in various fields and discovers knowledge for human understanding. However, different problems typically require parameter settings. Rule of thumb or trial-and-error methods are generally utilized to determine these may result poor settings unsatisfactory results. On the other hand, although a dataset contain numerous features, not all features beneficial classification algorithm. Therefore, novel scatter search-based approach (SS + DT) is proposed acquire optimal select subset that better To evaluate efficiency SS + DT approach, datasets UCI (University California, Irvine) Machine Learning Repository assess performance approach. Experimental results demonstrate algorithm obtained by than those approaches. When feature selection considered, accuracy rates on most increased. identify effectively best useful features.