摘要
为准确获悉商品住宅需求量,从经济因素与非经济因素两个方面识别商品住宅需求的影响因素,利用灰色关联分析法(GRA)提取商品住宅需求的主要影响因素,然后以此构建商品住宅需求预测指标体系,并将主要影响因素作为BP神经网络的输入向量,商品住宅销售量作为输出变量,采用遗传算法(GA)对BP神经网络权值与阈值进行寻优,建立基于GRA和GA-BP神经网络的商品住宅需求预测模型。以湖北省黄石市为例,对所建模型进行实证研究,并将预测结果与其他模型进行对比。数据结果显示:所建模型的相对误差在2%~8%范围内、平均相对误差为4.49%、均方根误差为6.14,预测精度相对最优;GRA和GA-BP神经网络模型用于商品住宅需求预测切实可行,可为其进行准确预测提供新方法。
In order to accurately know the demand for commercial housing,the influencing factors of commercial housing demand are identified from two aspects of economic factors and non-economic factors,and the main influencing factors of commercial housing demand are extracted by grey relational analysis(GRA),and then the demand for commercial housing is constructed.Prediction index system takes the main influencing factors as the input vector of the BP neural network and the sales volume of commercial housing as the output variable,and then uses the genetic algorithm(GA)to optimize the weights and thresholds of the BP neural network to build a neural network demand prediction model for commercial housing.Taking Huangshi city,Hubei province as an example,the model is empirically studied,and the prediction results are compared with other models.The data results show that the relative error of the model is between 2%and 8%,the average relative error is 4.49%,the root mean square error is 6.14,and the prediction accuracy is the best;GRA and GA-BP neural network models are used for commercial housing.Demand forecasting is practical and offers new ways to make accurate forecasts.
作者
邓英
邹璐
田学泽
DENG Ying;ZOU Lu;TIAN Xue-ze(School of Economics and Management,Changsha University of Science and Technology,Changsha 410114,China;School of Traffic and Transportation Engineering,Changsha University of Science and Technology,Changsha 410114,China)
出处
《陕西理工大学学报（自然科学版）》
2022年第4期75-84,共10页
Journal of Shaanxi University of Technology:Natural Science Edition
基金
湖南省教育厅科学研究项目(19A002)
长沙理工大学创新创业教育项目(JG201880,JG2019YB13)
长沙理工大学2021年度校级金课建设课程《财务管理学》资助项目
长沙理工大学研究生重点建设课程项目(Z0712019)。
关键词
商品住宅
需求预测
灰色关联分析
遗传算法
BP神经网络
commercial housing
demand forecast
grey relational analysis
genetic algorithm
BP neural network
