基于支持向量机的北京市房地产价格指数预测  

Prediction of price indices of Beijing real estate based on support vector machine

作　　者：梁坤[1] 聂会星[1] 徐枞巍[1] 

机构地区：[1]合肥工业大学管理学院,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2011年第4期588-592,共5页Journal of Hefei University of Technology：Natural Science

基　　金：国家自然科学基金重点资助项目(061119A2)

摘　　要：文章通过格兰杰因果关系检验建立影响房地产价格指数的相关指标体系,并基于支持向量机回归原理,利用Libsvm-2.89对北京市房屋销售价格指数进行预测,预测结果与实际接近;建立了预测绝对误差与支持向量率、迭代次数等的回归模型以得到误差修正因子对预测误差进行调整,提高了预测精度。This paper establishes a system of related indicators affecting price indices of real estate with Granger test,and forecasts the real estate selling price indices in Beijing City by Libsvm-2.89 based on the regression principle of support vector machine.The predicting results are close to the actual ones.The paper also sets up a regression model of prediction absolute error,support vector rate and iterations so as to get an error modifying factor to adjust the predictive encoding and advance the predicting accuracy.

关 键 词：房屋销售价格指数 格兰杰检验 支持向量机 修正因子 

分 类 号：C813[社会学—统计学]