基于LMD-XGBoost的短时生鲜物流需求预测

Prediction on the Short-Term Fresh Logistics Demand Based on LMD-XGBoost

随着生鲜物流行业的蓬勃发展,消费者对生鲜物流的要求也在进一步提高,传统需求预测模型已经难以满足市场需求。为解决传统预测方式难以有效应对短期生鲜物流需求的非线性关系和动态变化等问题,文章提出了LMD-XGBoost组合模型预测方法,对输入的物流需求曲线进行LMD分解,然后对分解所得的各分量进行XGBoost预测,最后对预测得出的分量进行逐一求和以得到最终结果。以某连锁超市的生鲜物流需求为例,对其日物流需求进行预测,证明该模型具备有效性和可行性,为解决非线性、强突变性短时物流曲线预测问题提供了方法参考。

With the booming development of the fresh logistics industry,consumers have further increased their requirements for the fresh logistics.Traditional prediction models are no longer able to meet the market demand.In order to address the shortcomings of traditional prediction methods in effectively dealing with the nonlinear relationship and dynamic changes of short-term fresh logistics demand,this paper proposes the LMD-XGBoost combination model prediction method.By decomposing the input logistics demand curve into LMD,the XGBoost prediction is performed on each component obtained from the decomposition,and finally,the predicted components are summed up one by one to obtain the final result.Taking the fresh logistics demand of a certain chain supermarket as an example,its daily logistics demand is predicted,and the results show that the model is effective and feasible,and can provide a method reference for solving the problem of non-linear and strongly sudden short-term logistics curve prediction.