昆明理工大学学报(自然科学版)

对多元线性回归模型及BP神经网络模型的理论及运用方法进行研究,采用SPSS及MATLAB软件分别建立多元性回归和BP神经网络预测模型,通过农村居民纯收入预测的算例,对多元线性回归和BP神经网络预测模型的拟合优度、初始数据的仿真与模拟能力和新数据的预测能力进行对比,数据结果表明BP神经网络预测模型优于多元线性回归预测模型.

The theory and application of multiple regression model and BP neural network model are studied in this paper. SPSS and MATLAB software are adopted to build multiple regression model and BP neural network model respectively,whose fitness,initial capability of simulation as well as capacity to predict new data are then compared through a case study of forecasting the net income of rural residents. It is shown through the comparisons that BP neural network prediction model is better than multiple regression prediction model.