计算机科学 ›› 2016, Vol. 43 ›› Issue (3): 38-43.doi: 10.11896/j.issn.1002-137X.2016.03.007

• 第十五届中国机器学习会议 • 上一篇    下一篇

特征背离和风险偏好分析的股价态势预测方法

姚宏亮,黄曼,王浩,李俊照   

  1. 合肥工业大学计算机与信息学院 合肥230009,合肥工业大学计算机与信息学院 合肥230009,合肥工业大学计算机与信息学院 合肥230009,合肥工业大学计算机与信息学院 合肥230009
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受国家自然科学基金(61175051,61070131,61175033)资助

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

YAO Hong-liang, HUANG Man, WANG Hao and LI Jun-zhao   

  • Online:2018-12-01 Published:2018-12-01

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。

关键词: 背离特征,风险偏好,DCPA算法,效用函数,RPDCA算法

Abstract: 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.

Key words: Deviated characteristic,Risk preference,DCPA algorithm,Utility function,RPDCA algorithm

[1] Xu Xing-jun,Yan Gang-feng.Price trend analysis based on the BP neural network[J].Zhejiang Finance:Capital&Insurance,2011(11):57-61(in Chinese) 徐兴军,颜钢锋.基于BP神经网络的股价趋势分析 [J].浙江金融:证券保险,2011(11):57-61
[2] Hsu C M.Forecasting Stock/futures Prices by Using NeuralNetworks with Feature Selection[C]∥Proceedings of 2011 6th IEEE Joint International Information Technology and Artificial Intelligence Conference(ITAIC 2011).2011:1-7
[3] Ma Li-li,Li Quan.Chinese Investors’ Risk Preferences in China[J].Statistical Research,2011,8(8):63-72(in Chinese) 马莉莉,李泉.中国投资者的风险偏好[J].统计研究,2011,8(8):63-72
[4] Duan Jing,Liu Yong-fang,He Qi.The Effects of Decision Ma-kers’ Roles and Related Variables on Risk Preferences[J].Acta Psychologica Sinica,2012,4(3):369-376(in Chinese) 段婧,刘永芳,何琪.决策者角色及相关变量对风险偏好的影响[J].心理学报,2012,4(3):369-376
[5] Chen Xu-hong.Extension and Application of Markowitz Mean-Variance Model[D].Shanghai:Shanghai Jiaotong University,2009(in Chinese) 陈许红.Markowitz均值-方差模型的推广及应用[D].上海:上海交通大学,2009
[6] Xu Xu-song,Chen Yan-bin.Portfolio choice model based on meanabsolute deviation and it’s simulated annealing algorithm[J].Journal of Management Sciences in China,2002,5(3):79-85(in Chinese) 徐绪松,陈彦斌.绝对离差证券组合投资模型及其模拟退火算法[J].管理科学学报,2002,5(3):79-85
[7] Huang Fu-kai.An Empirical Study of Downside Risk and Value Premium of A-Share Market:Based on Semi-Variance Analysis[J].South China finance,2014(3):57-62(in Chinese) 黄赋凯.我国A股价值溢价实证研究-基于半方差方法的分析[J].南方金融,2014(3):57-62
[8] Hu Xiao-wen,Hui Jun.Weighted semi-variance risk measuringmodel for portfolio investment[J].Journal of Hefei University of Technology(Natural Science),2007,0(4):518-520(in Chinese) 胡小文,惠军.加权半方差风险度量模型[J].合肥工业大学学报(自然科学版),2007,0(4):518-520
[9] Chen Ju-hua,Sui Shan-shan,Wang Jian-jiang.CompensationRegulation,Risk Preference and Enterprise Investment Efficiency:An Analysis Based on Meeting Effect Theory[C]∥Procee-dings of the Fourth Conference on Accounting on Both Sides of the Taiwan Straits.2012(in Chinese) 陈菊花,隋姗姗,王建将.薪酬管制、风险偏好与企业投资效率:基于迎合效应的分析[C]∥第四届海峡两岸会计学术研讨会论文集.2012
[10] Zhao Yan.Research and Application on BP Neural Network Algorithm[C]∥Proceedings of 2015 International Industrial Informatics and Computer Engineering Conference (IIICEC 2015).2015:1444-1447
[11] Wang Shuang-cheng.Bayesian Network Learning,Reasoningand Application[M].Shanghai:Lixin accounting press,2009(in Chinese) 王双成.贝叶斯网络学习、推理与应用[M].上海:立信会计出版社,2009
[12] Dong Hong-hui,Jia Li-min,Tian Yin,et al.Quantitatively Ana-lysis of Train Communication Network Based on Multi-attribute Utility Function[C]∥Proceedings of 17th International IEEE Conference on Intelligent Transportation Systems I.2014:2330-2335
[13] Chen Xiao-wei,Park G K.Expected Uncertain Utility Function and Its Risk Averse Analysis[C]∥Proceedings of the Thirteenth International Conference on Information and Management Sciences.2014:305-309
[14] Wu Jheng-long,Su Chen-chi,et al.Stock Price Predication using Combinational Features from Sentimental Analysis of Stock News and Technical Analysis of Trading Information[C]∥Proceedings of International Conference on Economics,Business and Management(ICEBM2012).2012:39-43

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 雷丽晖,王静. 可能性测度下的LTL模型检测并行化研究[J]. 计算机科学, 2018, 45(4): 71 -75, 88 .
[2] 夏庆勋,庄毅. 一种基于局部性原理的远程验证机制[J]. 计算机科学, 2018, 45(4): 148 -151, 162 .
[3] 厉柏伸,李领治,孙涌,朱艳琴. 基于伪梯度提升决策树的内网防御算法[J]. 计算机科学, 2018, 45(4): 157 -162 .
[4] 王欢,张云峰,张艳. 一种基于CFDs规则的修复序列快速判定方法[J]. 计算机科学, 2018, 45(3): 311 -316 .
[5] 孙启,金燕,何琨,徐凌轩. 用于求解混合车辆路径问题的混合进化算法[J]. 计算机科学, 2018, 45(4): 76 -82 .
[6] 张佳男,肖鸣宇. 带权混合支配问题的近似算法研究[J]. 计算机科学, 2018, 45(4): 83 -88 .
[7] 伍建辉,黄中祥,李武,吴健辉,彭鑫,张生. 城市道路建设时序决策的鲁棒优化[J]. 计算机科学, 2018, 45(4): 89 -93 .
[8] 刘琴. 计算机取证过程中基于约束的数据质量问题研究[J]. 计算机科学, 2018, 45(4): 169 -172 .
[9] 钟菲,杨斌. 基于主成分分析网络的车牌检测方法[J]. 计算机科学, 2018, 45(3): 268 -273 .
[10] 史雯隽,武继刚,罗裕春. 针对移动云计算任务迁移的快速高效调度算法[J]. 计算机科学, 2018, 45(4): 94 -99, 116 .