基于GA-ACO-BP神经网络的日用消费品物流需求预测

Logistics demand prediction of daily consumer goods based on GA-ACO-BP neural network

针对日用消费品的物流需求,从宏观经济发展水平、相关产业水平、消费能力、物流供应能力、互联网发展水平、贸易水平6个方面,采用灰色关联度分析法对影响因素的灰色关联度进行计算及排序,构建预测指标体系。考虑物流相关数据样本较少,其影响因素之间存在非线性,结合遗传算法的全局寻优能力和蚁群算法的并行计算能力,构建了基于遗传算法-蚁群优化-反向传播神经网络(genetic algorithm-ant colony optimization-back propagation neural network,GA-ACO-BP)的日用消费品物流需求预测模型。分别采用GA-ACO-BP模型、GA-BP模型和BP模型对全国日用消费品物流需求进行预测,结果表明,GA-ACO-BP模型更能拟合日用消费品物流需求变化,预测精度较高,为物流需求预测研究提供一种模型参考,具有一定的实用价值。

In response to the logistics demand of daily consumer goods,the grey correlation analysis method was used to calculate and sort the grey correlation degree of influencing factors from six aspects,namely,macroeconomic development level,relevant industry level,consumption capacity,logistics supply capacity,internet development level and trade level,and a prediction index system was constructed.Considering the small number of logistics-related data samples and the nonlinearity between their influencing factors,a daily consumer goods logistics demand prediction model based on the genetic algorithm-ant colony optimization-back propagation neural network(GA-ACO-BP neural network)was constructed by combining the global optimization ability of the genetic algorithm and the parallel computing ability of the ant colony algorithm.The GA-ACO-BP model,the GA-BP model and the BP model were used to predict the logistics demand of daily consumer goods nationwide,respectively.The results show that the GA-ACO-BP model can better fit the changes in logistics demand for daily consumer goods,with high prediction accuracy,and provides a model reference for logistics demand prediction research,which has certain practical value.