Prediction Model of Stock Price Based on Kernel Extreme Learning Machine
Chen Hai-yin · Neimenggu Shi-da xuebao. Zhexue shehui kexue hanwen ban · 2015
In order to conduct fast and accurate online prediction of stock price,a novel prediction model 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.