基于灰色回归模型广州市果蔬类生鲜农产品冷链物流需求预测

目的 通过对不同预测方法的误差进行对比研究，选取预测精度较高的方法，促进部门科学化决策。方法 从农产品供给、社会经济水平、冷链物流保障、居民规模与消费能力四大维度选取15个指标来构建影响因素指标体系，对影响因素与冷链物流需求进行灰色关联度分析。采用GM(1，1)、GM(1，6)与主成分-多元回归线性模型对果蔬类生鲜农产品冷链物流需求进行预测。结果 GM(1，1)预测模型、GM(1，6)预测模型、主成分-多元回归线性预测模型的预测误差分别为2.97%、1.70%、2.53%。结论 GM(1，6)预测模型预测精度最高，该模型适用于中短期的冷链物流需求预测，具有较高的应用价值。

Cold Chain Logistics Demand Forecast for Fresh Agricultural Products like Fruit and Vegetable in Guangzhou City Based on Gray Regression Model

The work aims to conduct a comparative study on the errors of different forecast methods, so as to select the method with higher accuracy and promote the scientific decision-making of relevant departments. Fifteen indicators were selected from the four dimensions of agricultural supply, socio-economic level, cold chain logistics security, size of the population and consumption capacity to construct the indicator system of influencing factors, and a gray correlation analysis was carried out between each influencing factor and cold chain logistics demand. The GM(1, 1) prediction model, GM(1, 6) prediction model and principal component-multiple regression linear prediction model were used to forecast cold chain logistics demand. The prediction errors of the GM(1, 1) prediction model, GM(1, 6) prediction model and principal component-multiple regression linear prediction model were 2.97%, 1.70% and 2.53%. The GM(1, 6) prediction model has high prediction accuracy, which is suitable for short and medium term cold chain logistics demand forecast and has high application value.