the construction process from the random forest ,analyzing the random factors about it and the use of empirical analyzed the factors influencing the random forest algorithm. From The experimental data drawing two conclusions: first, the classification accuracy of random forest algorithm increases along with the increase of the number of decision trees, but the efficiency of the algorithm with the increase of the number of decision tree; second there is a proportional increase between the classification accuracy of random forest and the number of characteristic variables F, the effect to the algorithm is not obvious when the value of F to a certain extent, but the efficiency of algorithm will decrease with the increase of the F value .