Study on Prediction of the Peasants’ Income Based on SVM

Abstract

China is a big agricultural country, effective prediction of peasants’ income is very important. This study mainly uses the SVM theory to predict the peasants’ income. By analyzing the influence factors of peasants’ income, establishes the index system, that is corresponding relationship of peasants’ income and factors of social influence, According to this index system, designs the prediction method of peasants’ income based on SVM. Bases on the statistical data of social factors and peasants’ income between 1990-2012 in china, to train the SVM model, at the same time, the kernel function and parameters of SVM used were setting and compared. The experimental results show that the accuracy of RBF function is 90.7%, the time is 98ms, has higher accuracy and faster computing speed.