摘要
物流业已成为我国第三产业的重要组成部分,高质量的物流业发展对促进经济高效循环、扩大内需等具有重大意义。为了提高物流需求预测的精确度,提出一种基于组合模型预测物流需求的方法:以山东省为例,将灰色预测、二次指数平滑预测及线性回归组合模型应用于物流需求的预测,选取山东省国民经济指标和货运量作为主要影响因素构建指标体系,基于山东省2002—2022年实际历史数据建立模型,将三种模型的优势进行创新性组合,构建科学的组合预测模型以预测山东省未来十年的物流需求量。物流需求的准确预测对山东省的宏观经济有着重要指导作用,可以使山东省物流产业规划与发展及制造业的经验决策更加切实有效,为山东省物流发展提供科学依据。
The logistics industry has already become an important part of China’s tertiary industry,and the development of a high-quality logistics industry is of great significance for promoting economic efficiency and circulation,as well as expanding domestic demand.To improve the accuracy of logistics demand forecasting,a method based on a combination model was proposed.Taking Shandong Province as an example,a combined model incorporating grey forecasting,quadratic exponential smoothing prediction,and linear regression was applied to predict logistics demand.The national economic indicators and freight volume of Shandong Province were selected as the main influencing factors to construct the index system.Based on actual historical data from Shandong Province from 2002 to 2022,the model was established,innovatively combining the advantages of the three models.This scientific combinatorial forecasting model was then used to predict the logistics demand of Shandong Province for the next ten years.The accurate prediction of logistics demand plays an important guiding role in the macro economy of Shandong Province.It enables more practical and effective decision-making in logistics industry planning and development,as well as in the manufacturing sector.Thus,it provides a scientific basis for the development of logistics in Shandong Province.
作者
程广华
王瑞
CHENG Guanghua;WANG Rui(School of Economics and Management,Anhui University of Science&Technology,Huainan 232001,China;School of Economics and Management,HuaiNan Normal University,Huainan 232038,China)
出处
《江苏理工学院学报》
2024年第3期56-66,共11页
Journal of Jiangsu University of Technology
基金
安徽省高校中青年教师培养行动重点项目“社会责任视角下平台供应链公益营销决策研究”(YQZD2023072)。
关键词
物流需求
灰色预测模型
二次指数平滑预测模型
线性回归预测模型
组合预测模型
logistics demand
grey prediction model
quadratic exponential smoothing prediction model
linear regression prediction model
combined prediction model
