基于因子分析与神经网络的区域物流需求预测  

Regional Logistics Demand Forecast Based on Factor Analysis and Neural Network

作　　者：刘智琦[1] 李春贵[1] 陈波[1] 

机构地区：[1]广西工学院计算机工程系,广西柳州545006

出　　处：《计算机仿真》2012年第6期359-362,共4页Computer Simulation

基　　金：广西科技攻关计划项目(桂科攻0815001-10);广西科技开发计划项目(桂科攻0992006-13)

摘　　要：研究区域物流需求预测问题。影响区域物流需求影响因子较多,因子之间呈非线性关系,导致预测模型结果复杂,运行时间长,预测精度低。为提高区域物流需求预测精度,提出一种因子分析和BP神经网络相结合的区域物流需求预测方法(FA-BP)。首先通过因子分析对影响因子进行降维处理,然后将降维后的区域物流需求数据作为BP神经网络的输入进行训练建立预测模型,最后得到区域物流需求的预测结果。对某省1993-2007年区域物流需求预测进行实例分析,结果证明FA-BP模型提高了区域物流需求预测精度,网络的收敛速度加快,在区域物流需求预测方面有着广阔的应用前景。In order to improve the forecast accuracy of regional logistics demand, we put forward a regional logis- tics demand forecasting method based on factor analysis and BP neural network （FA - BP）. Firstly, through factor a- nalysis, the dimensions of influencing factors was reducted. Then the regional logistics demand data were input to BP neural network for training, to establish the prediction model. Finally, the regional logistics demand forecasting re- suits were obtained. A regional logistics demand forecast of 1993 -2007 years was carried out and the results were analyzed. The results show that the FA - BP model improves the regional logistics demand forecast accuracy, speeds up the network convergence speed, and has a broad apolication DrosDect.

关 键 词：区域物流 神经网络 因子分析 预测方法 

分 类 号：F252[经济管理—国民经济]