基于最小二乘法的GM(1,1)模型在我国猪肉产量预测中的应用研究  

Application of GM(1,1) Model Based on Least Square Method in Pork Output Forecast in China

作　　者：王洁[1] 吴天魁 王波[1] WANG Jie WU Tian-kui WANG Bo(Business School, University of Shanghai for Science and Technology, Shanghai 200093,Chin)

机构地区：[1]上海理工大学管理学院,上海200093

出　　处：《经济数学》2016年第4期81-85,共5页Journal of Quantitative Economics

基　　金：国家自然科学基金(71401106)

摘　　要：猪肉产量受诸多因素影响,因此数据波动性大,并且具有小样本性及贫信息等特点.本文采用基于最小二乘法的GM(1,1)模型对我国未来几年内猪肉产量进行了短期预测.首先,介绍了GM(1,1)模型;然后,通过最小二乘法的原理弱化波动较大的数据,减少随机性,加强规律性,建立基于最小二乘法的GM(1,1)模型;其次,结合2008至2014年我国猪肉产量数据建立预测模型;最后,使用2014年数据对模型的可靠性进行验证,基于最小二乘法的GM(1,1)模型的预测结果更加接近实际值.预测结果显示未来3年中国猪肉产量将持续增加.该模型为其他相关预测提供了理论依据,也便于我国对未来猪肉产品市场进行宏观调控,维持猪肉市场平衡,避免猪肉价格波动风险.Pork production is affected by many factors, so it＇s data volatility is large, and has the characteristics of small sample and poor information and so on. In this paper, GM （1,1） model based on the least squares method was used to forecast the pork production in China in the coming years. First of all, the GM （1,1） model was introduced, and the principle of least squares was used to weaken the data with large fluctuation, to reduce the randomness, to strengthen the regularity and to build the GM （1,1） model based on the least square method. The forecast model of pork production in China was established with data of 2008 to 2014, and the reliability of the model was validated by the data of 2014 and the predictions of GM （1,1） model based on the least squares method was more close to the actual value. The forecast results show that China＇s pork production will continue to increase, in the next three years. This model provides a theoretical basis for other related forecasts. It also facil- itates the macro regulation of the pork market in the future and maintains the pork market balance to avoid the risk of pork price fluctuation.

关 键 词：预测 猪肉产量 GM(1 1)模型 最小二乘法 

分 类 号：F307.3[经济管理—产业经济]