Modify Random Forest Algorithm Using Hybrid Feature Selection Method
Ahmed T. Sadiq‎, Karrar Shareef Musawi · International Journal on Perceptive and Cognitive Computing · 2018
The Importance of Random Forrest(RF) is one of the most powerful methods of machine learning in Decision Tree. The Proposed hybrid feature selection for Random Forest depend on two measure Information Gain and Gini Index in varying percentages based on weight. In this paper, we tend to propose a modify Random Forrest algorithm named Random Forest algorithm using hybrid feature selection that uses hybrid feature selection instead of using one feature selection. The main plan is to computation the Information Gain for all random selection feature then search for the best split point in the node that gives the best value for a hybrid equation with Gini Index. The experimental results on the dataset showed that the proposed modification is better than the classic Random Forest compared to the standard static Random Forest the hybrid feature selection Random Forrest shows significant improvement in accuracy measure.