摘要
提出了一种用于股票价格预测的人工神经网络(ANN),隐马尔可夫模型(HMM)和粒子群优化算法(PSO)的组合模型-APHMM模型。在APHMM模型中,ANN算法将股票的每日开盘价、最高价、最低价与收盘价转换为相互独立的量并作为HMM的输入。然后,利用PSO算法对HMM的参数初始值进行优化,并用Baum-Welch算法进行参数训练。经过训练后的HMM在历史数据中找出一组与今天股票的上述4个指标模式最相似数据,加权平均计算每个数据与它后一天的收盘价格差,则今天的股票收盘价加上这个加权平均价格差便为预测的股票收盘价。实验结果表明,APHMM模型具有良好的预测性能。
A fusion model APHMM is proposed by combining the hidden Markov model （HMM）, artificial neural networks （ANN） and particle swarm optimization （PSO） to forecast financial market behavior. In APHMM, use ANN to transform the daily stock price into independent sets of values and become input to HMM. Then draw on PSO to optimize the initial parameters of HMM. The trained HMM is used to identify and locate similar patterns in the historical data. The price differences between the matched days and the respective next day are calculated. Finally, a weighted average of the price differences of similar patterns is obtained to prepare a forecast for the required next day. Forecasts are obtained for a number of securities that show APHMM is feasible.
出处
《计算机工程与设计》
CSCD
北大核心
2009年第21期4945-4948,共4页
Computer Engineering and Design
