关键词: 随机森林, 袋外估计, 网格搜索, 参数优化

Abstract: Random forest is an effective ensemble learning method, which is widely used in pattern recognition. In order to get higher accuracy, it is necessary to optimize the parameter of random forest. Based on generalization error of out-of-bag estimates, this paper proposes a parameter optimization method for a random forest with improved grid search. The parameter of the number of decision trees and candidate splitting attributes is optimized to improve accuracy. The simulation results demonstrates that optimized parameter by the method proposed in this paper makes the classification performance of random forest better.

Key words: random forest, out-of-bag estimates, grid search, parameter optimization