基于BP神经网络组合模型的广东省区域物流需求能力预测  

Forecasting of Regional Logistics Demand Capacity in Guangdong Province Based on BP Neural Network Combination Model

作　　者：赵文德 黄丽娟 胡子瑜[1] Zhao Wende;Huang Lijuan;Hu Ziyu(School of Management,Guangzhou Panyu Polytechnic,Guangzhou 511483;Business Administration School,Guangzhou University,Guangzhou 510006,China)

机构地区：[1]广州番禺职业技术学院管理学院,广东广州511483 [2]广州大学工商管理学院,广东广州510006

出　　处：《物流技术》2020年第12期49-56,66,共9页Logistics Technology

基　　金：广东省教育厅特色创新类项目(2019GWTSCX069);广州市哲学社会科学发展“十三五”规划2020年度共建课题(2020GZGJ289);广州番禺职业技术学院“十三五”(第三批)科研项目(2020SK27)。

摘　　要：首先分析了国内外关于物流需求能力预测的研究现状,构建了以物流消费能力、物流基础能力、物流信息能力为一级指标的综合预测指标体系;然后运用多项式回归、ARIMA和BP神经网络等模型对广东省区域物流能力预测进行实证分析。研究结果表明,BP神经网络模型能够更好地实现区域物流能力的预测,物流基础能力成为影响区域物流发展的关键因素,能够为各级别政府制定科学有效的区域物流发展顶层设计和政策落地提供决策支撑。In this paper,we first analyzed the current research status of logistics demand capability prediction both at home and abroad,and constructed a comprehensive forecasting index system with logistics consumption capability,logistics basic capability,and logistics information capability as the first-level indicators.Then using polynomial regression,ARIMA and BP neural network,we had an empirical analysis on the forecasting of the regional logistics capacity in Guangdong Province.The result showed that the BP neural network model could better forecast regional logistics capacity,and logistics basic capacity is the key factor affecting the development of regional logistics.

关 键 词：区域物流 需求能力预测 多元回归 BP神经网络 ARIMA模型 广东 

分 类 号：F224.0[经济管理—国民经济] F259.27