特征背离和风险偏好分析的股价态势预测方法  

Trend Forecast of Stock Price Based on Deviated Characteristics and Risk Preference

作　　者：姚宏亮[1] 黄曼[1] 王浩[1] 李俊照[1] 

机构地区：[1]合肥工业大学计算机与信息学院,合肥230009

出　　处：《计算机科学》2016年第3期38-43,共6页Computer Science

基　　金：国家自然科学基金(61175051;61070131;61175033)资助

摘　　要：由于股价走势与技术指标走势存在不一致性,基于技术特征的股价态势预测算法效果不佳。从特征背离角度提出了一种股价态势预测算法(Deviated Characterisitics Predict Algorithm,DCPA),该算法首先进行背离特征的提取,并计算特征的背离程度,然后根据特征的背离程度值和股票的收盘价利用BP网络进行股价态势预测。由于当市场风险偏好高时特征背离与股价态势之间相关性很弱,因此在DCPA算法的基础上提出了一种风险偏好的股价态势预测算法(Risk Preference Based Deviated Characterisitics predict Algorithm,RPDCA)。首先提取与风险偏好相关的特征,利用风险偏好计算模型获得当前的市场风险偏好类型;进而利用贝叶斯网络学习风险偏好、背离特征与股价走势之间的关系,并利用结点非对称信息熵分析风险偏好与背离特征之间的依赖关系;最后根据风险偏好与背离特征之间关系的变化,自适应性地利用BP网络预测股价态势。在实际数据上的实验比较与分析结果表明,RPDCA算法在股市短期预测中具有更高的预测精度。Due to the inconsistent tendency of stock price and technical index,the share price trend prediction algorithm based on the technical features performs poorly.A share price trend prediction algorithm from the point of deviated characteristics （DCPA） was proposed.Deviated features firstly are extracted,the degree of swerve is calculated,and then the trend of price is forecasted by BP neural network according to the degree of swerve and the stock＇s closing price.While the risk appetite is high,the correlation between stock price trend and deviated characteristics is weak,thus a risk preference based share price trend prediction algorithm named RPDCA was put forward on the basis of DCPA algorithm.Firstly,features which are associated with risk appetite are extracted and the current market risk preference type is acquired through the risk appetite computational model.Secondly,by means of Bayesian network,the structural relationship among risk appetite,deviated characteristics and the trend of stock price is learned,and then the interdependent relationship between risk appetite and deviated characteristics is analyzed by using node asymmetric information entropy.Last,the trend of stock price is forecasted self-adaptedly according to the relationship between risk appetite and deviated characteristics by BP neural network.Based on the comparison and analysis on the actual data,the experimental results show that the RPDCA algorithm has higher precision of short-term prediction.

关 键 词：背离特征 风险偏好 DCPA算法 效用函数 RPDCA算法 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]