摘要
销售预测是企业经营活动中不可缺少的一个环节,预测的准确性直接关系到农资网站销售经营活动的成败。因此,先利用因子分析法,优化传统BP神经网络算法,再建立起适合农资网站的销售预测模型,最后将该模型具体应用到某农资网站,实现对该农资网站的销售预测。实验表明,优化后的BP神经网络算法不仅降低了迭代次数,提高了收敛速度,而且简化了网络结构,提高了预测准确度。
Sales forecasting is an indispensable part of business activities.The accuracy of forecasting is directly related to the success or failure of sales and operation activities of agricultural website.Therefore,the factor analysis method was used to optimize the traditional BP neural network algorithm,and then a sales forecasting model suitable for the agricultural website was established.Finally,the model was applied to a certain agricultural website to realize the sales forecasting of the agricultural website.Experiments show that the optimized BP neural network algorithm not only reduces the number of iterations and improves the convergence rate,but also simplifies the network topology and improves the prediction accuracy.
作者
周朝进
王玉珍
ZHOU Chaojin;WANG Yuzhen(Silk Road Economic Research Institute,Lanzhou University of Finance and Economics,Lanzhou 730020,China;School of Information Engineering,Lanzhou University of Finance and Economics,Lanzhou 730020,China)
出处
《邵阳学院学报（自然科学版）》
2019年第1期52-59,共8页
Journal of Shaoyang University：Natural Science Edition
基金
兰州财经大学丝绸之路经济研究院项目(JYYY201704)
关键词
销售预测
因子分析法
BP神经网络
农资网站
sales forecasting
factor analysis
BP neural network
agricultural resources website
