基于季节指数调整的GM-BP模型对中国大米集贸市场价格的预测分析  

Predicative analysis of marketprice of China’s rice based on GM-BP model of seasonal index adjustment

作　　者：毕硕本 邱湘开[2,3] 汤智 BI Shuo-ben;QIU Xiang-kai;TANG Zhi(School of Geographical Sciences,Nanjing University of Information Science and Technology,Nanjing,Jiangsu 210044;Research Institute for the History of Science and Technology,Nanjing University of Information Science and Technology,Nanjing,Jiangsu 210044;School of Journalism and Communication,Minjiang University,Fuzhou,Fujian 350108)

机构地区：[1]南京信息工程大学地理科学学院,江苏南京210044 [2]南京信息工程大学科学技术史研究院,江苏南京210044 [3]闽江学院新闻传播学院,福建福州350108

出　　处：《价格月刊》2021年第7期55-60,共6页

基　　金：2019年国家自然科学基金“面向大数据的位置信息挖掘与推荐方法研究——以南京市出租车GPS数据为例”(编号:41971340)。

摘　　要：作为农业大国,大米价格的稳定,对于农民收入、粮食安全、经济健康发展有着重要意义。对大米价格做出科学准确预测,将有助于政府相关部门采取及时有效的措施,增加农民收入。选取2006年1月-2017年12月大米集贸市场价格的月度数据,先对其进行季节指数调整,再采用GM-BP神经网络组合模型对其进行价格预测分析,并与无季节调整的BP神经网络模型和季节调整后的BP神经网络模型预测结果进行比较。结果表明:基于季节指数调整的GM-BP神经网络模型的预测精度具有准确性高等特点。As a big agricultural country,the stability of rice price is of great significance for farmers’income,food security and healthy economic development.Making scientific and accurate prediction of rice price will help relevant government departments to take timely and effective measures to increase farmers’income.Based on the monthly data of rice market price from January 2006 to December 2017,this paper first adjusted its seasonal index,and then used the GM-BP neural network combination model for price predicative analysis.The prediction results of the BP neural network model were compared with the seasonally adjusted BP neural network model.The results show that the prediction accuracy of the GM-BP neural network model based on seasonal index adjustment has the characteristics of high accuracy.

关 键 词：季节指数调整 灰色模型GMBP神经网络 GM-BP模型 

分 类 号：F323.7[经济管理—产业经济]