基于灰色BP神经网络的河南省物流需求预测

Prediction of Logistics Demand in Henan Province Based on Grey BP Neural Network

摘要: 构建“灰色关联度–灰色预测-BP神经网络”组合预测模型，能够有效筛选关键影响因子，克服单一模型局限性，对区域物流需求进行预测。文章选取河南省2011~2024年的货运量为变量依据，运用BP神经网络对河南省的近三年物流需求量情况进行预测。首先提出可能会影响物流需求量的9个因素，然后运用灰色关联度分析得出关联度最高的8个因素，将得出的8个因素运用灰色预测得到2025~2027年的预测值，最后将得出的预测值作为BP神经网络的输入变量，得到河南省2025~2027年物流需求变量的预测值。结果表明：河南省物流需求在未来三年里是逐年上升的，并提出相关政策建议。

Abstract: A combined forecasting model of “grey correlation degree-grey prediction-BP neural network” is constructed to effectively screen the key influencing factors, overcome the limitations of a single model, and predict the regional logistics demand. The article selects the freight volume of Henan Province from 2011 to 2024 as the variable basis, and uses a BP neural network to predict the logistics demand of Henan Province in the past three years. Firstly, 9 factors that may affect logistics demand are proposed. Grey correlation analysis is used to identify the 8 factors with the highest correlation degree. The predicted values for 2025~2027 are obtained using grey prediction, and the predicted values are used as input variables for the BP neural network to obtain the predicted values of logistics demand variables in Henan Province from 2025 to 2027. The results indicate that the logistics demand in Henan Province will increase year by year in the next three years, and relevant policy recommendations have been proposed.