基于在线核极限学习机的股票价格预测模型  

Prediction Model of Stock Price Based on Kernel Extreme Learning Machine

作　　者：陈海英[1] 刘洋[2] 

机构地区：[1]华中农业大学楚天学院,湖北武汉430205 [2]信阳职业技术学院,河南信阳464000

出　　处：《内蒙古师范大学学报（自然科学汉文版）》2015年第2期174-178,共5页Journal of Inner Mongolia Normal University(Natural Science Edition)

基　　金：湖北省高校省级教学研究项目(2012458);华中农业大学楚天学院科研项目(K201405)

摘　　要：为了对股票价格进行准确、快速的在线预测,提出一种在线核极限学习机算法(OL-KELM)的股票价格预测模型.首先收集股票价格数据,采用相空间重构理论建立学习样本,然后将学习样本输入在线核极限学习机中进行学习,建立股票价格预测模型,最后对国药股份(600511)股票收盘价进行仿真实验.结果表明,相对于其他股票价格预测模型,OL-KELM提高了股票价格预测的准确性,可以准确地刻画股票价格的变化趋势.In order to conduct fast and accurate online prediction of stock price,a novel prediction mod-el of stock price based on kernel extreme learning machine algorithm is proposed.Firstly,the stock price data are collected and learning samples are reconstructed by phase space reconstruction theory,and the samples are input to online kernel extreme learning machine to learn and established stock price predicting model,finally,the simulation experiment is carried out on guoyao shares （600010）.The results show that the proposed model has improved prediction precision of stock price compared other stock price predicting models,and it can describe the change rule of stock price.

关 键 词：股票价格 核极限学习机 在线预测 鲁棒性 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]