改革开放以来,中国居民收入稳步上涨,但收入差距却越来越大。对于个人收入的分析也成了研究的重点。本文利用matlab R2012a建立了BP神经网络和支持向量机算法模型,得到了两个模型在研究个人收入预测应用中总体预测准确率、均方误差MSE和决定系数R2的值。结果表明,相比于BP神经网络,支持向量机预测准确率更高,模型拟合度更好,具有更好的预测效能。 Since the reform and opening up, the income of Chinese residents has risen steadily, but the income gap has been growing. The analysis of personal income has also become the focus of research. In this paper, using matlab R2012a established BP neural network and support vector machine algorithm model, obtained two models in the study of personal income forecasting application of the overall prediction accuracy, mean square error MSE and decision coefficient R2 value. The results show that compared with BP neural network, the SVM prediction accuracy is higher, the model fitting degree is better, and the prediction performance is better.