自适应参数的AOSVR算法及其在股票预测中应用  

AOSVR algorithm with adaptive parameters and its application to stock market forecast

作　　者：吴微[1] 张凌[1] 

机构地区：[1]大连理工大学应用数学系,辽宁大连116024

出　　处：《大连理工大学学报》2009年第4期605-610,共6页Journal of Dalian University of Technology

基　　金：国家自然科学基金资助项目(10471017;10871220);教育部青年骨干教师基金资助项目(3004-082502)

摘　　要：以股票预测为背景,在一种在线SVR算法AOSVR中,引入Cherkassky参数选择策略,形成自适应参数的AOSVR算法.根据时间序列的变化,通过在线调整SVR参数达到更好的预测精度和泛化能力.另外,针对股票市场特性,利用AOSVR的"忘记"阈值丢掉早期数据来集中刻画近期的股市特点.将自适应参数的AOSVR算法应用到上证综合指数构成的时间序列上,取得了良好的预测效果.With the application to stock market forecast as background, Cherkassky＇s parameter-selection method is embedded into an online support vector regression algorithm AOSVR, resulting in an adaptive AOSVR algorithm. Forecast accuracy and generalization ability are much improved through online adapting the SVR parameters according to the movement of the time series. Meanwhile, based on the characteristics of stock market, a ＂forgetting＂ bias is used to ignore to some extent the earlier data and to concentrate on the recent data. The adaptive AOSVR algorithm is successfully applied to the forecast of the time series of Shanghai stock market index.

关 键 词：在线支持向量机回归算法 参数选择 非稳定时间序列 股票预测 

分 类 号：O242[理学—计算数学]