基于灰色回归模型的农产品冷链物流需求分析及预测

Analysis and Forecast on Cold Chain Logistics Demand of Agricultural Products Based on Grey Regression Model

在“双循环”背景下,农产品冷链物流对提升农业价值链、释放内需消费潜力具有重要意义。为精准预测市场需求,针对我国冷链物流行业统计工作滞后、样本数据量少、影响因素多的情况,在分析冷链物流市场需求特征的基础上,将灰色-回归组合模型应用于我国农产品冷链物流市场需求预测,设计了我国冷链物流市场需求预测指标,从产品供给、经济社会、居民消费、行业规模四大维度选取6个典型数据指标构建影响因素指标体系,分析了各影响因素与市场需求的灰色关联关系。通过对2011—2020年我国冷链物流市场需求进行建模,建立了由第三产业对GDP贡献率、冷藏车保有量两个指标为自变量的回归模型,对2021—2025年冷链物流市场需求量进行了预测。实证结果表明:灰色预测、多元线性回归的组合模型预测值平均相对误差仅为0.82%,相比单一灰色预测和多元线性回归,对我国冷链物流市场需求总量的中短期预测具有较高的可信度和较好的精准度。分析结果显示:未来5年我国冷链物流市场需求仍呈明显的上升趋势,增速在6%~9%左右。基于关联分析和预测模型结果,从加快补齐生鲜农产品“最初一公里”供给短板、加强冷藏保温车辆等设施设备有效供给和加大冷链物流市场主体培育力度等方面提出了促进我国冷链物流高质量发展的相关建议。

Under the background of the construction of double-cycle development pattern,the cold chain logistics of agricultural products is of great significance to enhance the agricultural value chain and release the potential of domestic consumption.In order to accurately predict the market demand,in view of the lagging statistical work,small amount of sample data and many influencing factors of cold chain logistics industry in China,based on the analysis of the market demand characteristics of cold chain logistics,the grey-regression combination model is applied to the prediction of domestic agricultural product cold chain logistics market demand,and the prediction indictor of domestic cold chain logistics market demand is designed.Six typical data indicators are selected from the dimensions of product supply,economic society,household consumption and industry scale to construct an influencing factor indicator system,and the grey correlation between each influencing factor and market demand is analyzed.By modeling the domestic cold chain logistics market demand from 2011 to 2020,a regression model with the contribution rate of the tertiary industry to GDP and the number of refrigerated vehicles as the independent variables is established,and the cold chain logistics market demand from 2021 to 2025 is predicted.The empirical result shows that the average relative error of the combination model of grey prediction and multiple linear regression is only 0.82%,compared with single grey prediction and multiple linear regression,the combination model has higher reliability and better accuracy for the medium and short-term prediction of domestic total demand of cold chain logistics market.The analysis result shows that the demand of domestic cold chain logistics market will still show an obvious upward trend in the next 5 years,with a growth rate of about 6%-9%.Based on the result of correlation analysis and prediction model,relevant suggestions for promoting the high-quality development of domestic cold chain logistics are put forward,including accelerating the replenishment of the“first kilometer”supply shortcomings of fresh agricultural products,strengthening the effective supply of facilities and equipment such as refrigerated and insulated vehicles,and strengthening the cultivation of cold chain logistics market players.