[摘　要]　尝试将支持向机算法应用于房地产需求量预测。该算法能针对在样本有限的情况下，采用结构风险最小化准则，把学习问题转化为一个二次规划问题来获得最优解。预测结果利用可信度p0、关联度R、后验差比值C和小误差概率p等项指标检验，证实了所建模型是可靠的，可行的。

[关键词]　支持向量机（SVM）；房地产；需求量；预测

Abstract: The paper tried to apply the Support Vector Machine（SVM） to the forecast of the demands of real estate. The method can transfer the learning problem into a second planning to acquire the optimal solution according to the principle of structure risk minimum under limited samples situation.From the tested results calculated by some indexes, such as reliability p0, association degree R, correlative value of posterior error C and micro-error probability p, the model was proved to be reliable and feasible in the forecast of the demands of real estate.

Key words: support vector machine（SVM）; real estate; demand; forecast

[参考文献]

[1]VladimirN，Vapnik.统计学习理论的本质[M].张学工，译.北京:清华大学出版社，2000.

[2]张学工.关于统计学习理论与支持向量机[J].自动化学报，2000，26（1）:32-43.

[3]Cortes C， Vapnikc V. Support-vector networks. Machine Learning [J].1995（20）:273-297.

[4]http://www.csie.ntu.edu.tw/~cjlin/libsvm/.

[5]易丹辉.数据分析与Eviews 应用[M]北京:中国统计出版社，2002:43-45.

建筑经济，2009（5）：60-62