Generational Feature Selection using Random Forest Approach

Feature selection process is crucial step in many different knowledge discovery experiments. Here, some initial attempt to Generational Feature Selection using random forest were presented. This approach devotes to application of random forest algorithm to estimate importance of attributes with recursive application of generational feature selection. This method apply removing of selected features from dataset and then creates next generation of important feature set. This process goes until the most important feature will be a random value. Implemented method were applied on three artificial and real, medical datasets and the results of selection and classification are presented. The results were significantly better for limited datasets.