物流网络中多地区配送需求预测方法

发布时间：2019-05-27 04:01

【摘要】：物流网络较为复杂,当前预测方法只采用一种方法对物流网络中多地区配送需求进行预测,无法保证预测精度。提出一种新的需求预测方法,通过两个或两个以上不一样的预测方法,对物流网络中多地区配送需求进行预测,构建物流网络中多地区配送需求组合预测模型,对不同方法进行加权组合,通过熵值法对组合预测模型的组合权重进行计算,充分利用不同预测方法的优点,获取较优的预测结果。通过残差检验和后验差检验,对组合预测模型的配送需求预测能力进行评价。实验结果表明,所提方法具有很高的预测精度。
[Abstract]:The logistics network is more complex. The current forecasting method only uses one method to predict the multi-regional distribution demand in the logistics network, which can not guarantee the prediction accuracy. In this paper, a new demand forecasting method is proposed. Through two or more different forecasting methods, the multi-regional distribution demand in the logistics network is forecasted, and the multi-regional distribution demand combination forecasting model in the logistics network is constructed. The weighted combination of different methods is carried out, and the combined weight of the combined prediction model is calculated by entropy method, and the better prediction results are obtained by making full use of the advantages of different prediction methods. The distribution demand forecasting ability of the combined forecasting model is evaluated by residual test and posterior error test. The experimental results show that the proposed method has high prediction accuracy.
【作者单位】：云南师范大学文理学院;
【分类号】：F259.2

【参考文献】