基于神经网络的需求预测模型

Forecasting model based on neural network

零售业的销售过程中积累了大量数据,如何从这些海量数据中提取知识、建立有效的需求预测模型,为零售商提供市场和趋势分析、降低库存成本是零售行业亟待解决的问题。在传统的零售业需求预测模型——Holt-Winter模型中应用神经网络方法,使得需求预测不依赖于数学模型的精度,预测模型中的季节性影响因子等参数能够根据预测误差作相应调整,避免了传统算法中误差的累积,大大提高了预测精度。利用Excel内嵌的VBA实现了该算法,使需求预测能够根据用户需要实现,并提供可视化的结果。

To obtain the inherent laws from large amounts of data records in retail industry and to provide valuable information for retailers,this paper presents a neural-network-based forecasting algorithm,which adopts Holt-Winters＇model and a neural network.Different from traditional forecasting algorithms,this algorithm rearranges Holt-Winters model,and builds a neural network on it.Furthermore,it puts forward a training algorithm to optimize the adjustable neural network weights by minimizing a defined cost function,which has greatly improved the forecasting accuracy.In addition,by applying the Excel VBA embedded,this paper achieves the realization of demand forecasting in accordance with user needs,and provides visualization of the results.