基于PCA-GA-BP神经网络模型对安徽省物流需求量预测  

Forecast of logistics demand in Anhui province based on PCA-GABP neural network model

作　　者：聂轶文 王韡 NIE Yiwen;WANG Wei(School of Information Engineering,Fuyang Normal University,Fuyang Anhui 236041,China;Anhui Telecom Hefei Branch,Hefei Anhui 230031,China)

机构地区：[1]阜阳师范大学信息工程学院,安徽阜阳236037 [2]安徽电信合肥分公司,安徽合肥230031

出　　处：《阜阳师范大学学报（自然科学版）》2023年第4期96-102,共7页Journal of Fuyang Normal University:Natural Science

基　　金：阜阳师范大学校级项目(2019FXGSK02)资助。

摘　　要：物流业健康稳序发展是经济发展的重要支撑,物流需求量的预测是物流需求量预测是科学布局物流网络枢纽的基础。为提升物流需求预测的准确度,本文构建了一种基于主成分分析的GA-BP神经网络模型,首先对原始指标进行降维处理(PCA)提取主成分,将这些由原始指标线性组合而成的主成分作为模型的输入,再利用遗传算法对BP网络参数进行优化,选取2000-2019安徽省相关经济发展指标数据进行训练和测试,测试结果平均绝对百分比误差(MAPE)仅为6.6%。从而表明本文构建的GA-BP神经网络模型对区域物流需求预测是有效的。The healthy and orderly development of the logistics industry is an important support for economic growth,and accurate prediction of logistics demand is the basis for scientifically planning logistics network hubs.To improve the accuracy of logistics demand forecasting,this paper proposes a GA-BP neural network model based on Principal Component Analysis(PCA).Firstly,the original indicators are subjected to dimensionality reduction through PCA to extract principal components.These principal components,which are linear combinations of the original indicators,are used as inputs to the model.Then,genetic algorithm is applied to optimize the parameters of the BP neural network.The model is trained and tested using relevant economic development indicator data from Anhui Province from 2000 to 2019.The average Mean Absolute Percentage Error(MAPE)of the test results is only 6.6%.This indicates that the GA-BP neural network model constructed in this paper is effective for regional logistics demand forecasting.

关 键 词：区域物流需求 主成分分析 GA-BP神经网络 

分 类 号：C915[经济管理]