期刊导航

论文摘要

基于概率后缀树的股票时间序列预测方法研究

Research of Stock Time Series Based on probabilistic Suffix Tree

作者:程小林(四川大学计算机学院);郑兴(四川大学计算机学院);李旭伟(四川大学计算机学院)

Author:CHENG Xiao-Lin(College of Computer Science, Sichuan University);ZHENG Xing(College of Computer Science, Sichuan University);LI Xu-Wei(College of Computer Science, Sichuan University)

收稿日期:2017-07-08          年卷(期)页码:2018,55(1):0061-0066

期刊名称:四川大学学报: 自然科学版

Journal Name:Journal of Sichuan University (Natural Science Edition)

关键字:股票数据挖掘,时间序列符号化,高斯混合模型聚类,概率后缀树

Key words:stock data mining, time series symbolization, Gaussian Mixture Modeling, , Probabilistic Suffix Tree

基金项目:国家自然科学基金 61173099

中文摘要

本文在时间序列符号化基础上,引入概率后缀树(Probabilistic Suffix Tree,PST)模型,构建基于时间序列符号化和概率后缀树相结合的股票预测模型。本文选择在沪深300的10股票数据上将预测模型与传统的马尔科夫模型(Markov Model,MM)和自回归移动平均模型(Auto Regressive Moving Average Model,ARMA)进行对比,结果显示本文提出的股票预测模型优于MM模型和ARMA模型,验证了本文所提出的预测模型在投资收益上的有效性。

英文摘要

this paper introduces a Probabilistic Suffix Tree (PST) method based on the time series symbolization, and constructs a stock forecasting model based on the combination of time series symbolizationa and PST. In addition, the Markov Model MM and the Auto Regressive Moving Average Model (ARMA) are compared with the forecasting model of this paper.The stock of 10 CSI 300 indices is used as the experimental sample. The results show that the stock forecasting model proposed in this paper is better than the MM model and the ARMA model,and proves the validity of the forecasting model proposed in this paper.

关闭

Copyright © 2020四川大学期刊社 版权所有.

地址:成都市一环路南一段24号

邮编:610065