|本期目录/Table of Contents|

[1]傅中杰,吴清强*.基于隐马尔科夫模型的市场指数量化择时研究[J].厦门大学学报(自然科学版),2018,57(03):404-412.[doi:10.6043/j.issn.0438-0479.201710011]
 FU Zhongjie,WU Qingqiang*.Research of Market Index Quantitative Timing Based on Hidden Markov Model[J].Journal of Xiamen University(Natural Science),2018,57(03):404-412.[doi:10.6043/j.issn.0438-0479.201710011]
点击复制

基于隐马尔科夫模型的市场指数量化择时研究(PDF/HTML)
分享到:

《厦门大学学报(自然科学版)》[ISSN:0438-0479/CN:35-1070/N]

卷:
57卷
期数:
2018年03期
页码:
404-412
栏目:
研究论文
出版日期:
2018-05-31

文章信息/Info

Title:
Research of Market Index Quantitative Timing Based on Hidden Markov Model
文章编号:
0438-0479(2018)03-0404-09
作者:
傅中杰吴清强*
厦门大学软件学院,福建 厦门 361005
Author(s):
FU ZhongjieWU Qingqiang*
Software School of Xiamen University,Xiamen 361005,China
关键词:
隐马尔科夫模型 市场择时 交易策略
Keywords:
hidden Markov model(HMM) market timing trading strategy
分类号:
TP 391
DOI:
10.6043/j.issn.0438-0479.201710011
文献标志码:
A
摘要:
量化择时是量化投资领域的重要组成,主要负责评判何时进行交易.为了验证隐马尔科夫模型(hidden Markov model,HMM)应用到量化择时的可行性,基于股票市场原始数据计算得到候选特征集,并利用HMM对各个单特征进行特征筛选,最后使用选出的特征集训练得到综合模型,预测交易日的市场状态.实验结果表明,基于HMM的交易策略比双均线策略和基于k-均值(k-means)聚类的策略都有更好的表现,且具有较强的识别市场状态、规避系统性风险以及获取超额收益的能力.
Abstract:
Quantitative market timing constitutes an important part of quantitative investment to choose the best trading opportunity.To verify the feasibility of applying hidden markov model(HMM)to quantitative market timing,we creatively calculate candidate features set based on raw data,use HMM to test performance on each single feature,and train a comprehensive model using selected features to predict the market state of the next trading day.Experimental results show that HMM-based strategy enjoys better stability and profitability compared with strategies based on moving average or ans.Finally,HMM can skillfully identify market states,avoid systematic risk and obtain excess return.

参考文献/References:

[1] GUIDOLIN M,TIMMERMANN A.Asset allocation under multivariate regime switching[J].Journal of Economic Dynamics & Control,2007,31(11):3503-3544.
[2] DE ANGELIS L,PAAS L J.A dynamic analysis of stock markets using a hidden Markov model[J].Journal of Applied Statistics,2013,40(8):1682-1700.
[3] SALHI K,DEACONU M,LEJAY A,et al.Regime switching model for financial data:empirical risk analysis[J].Physica a-Statistical Mechanics and Its Applications,2016,461:148-157.
[4] 杨新斌,黄晓娟.基于支持向量机的股票价格预测研究[J].计算机仿真,2010,27(9):302-305.
[5] 谢国强.基于支持向量回归机的股票价格预测[J].计算机仿真,2012,29(4):379-382.
[6] CAO L,TAY F E H.Financial forecasting using support vector machines[J].Neural Computing & Applications,2010,10(2):184-192.
[7] GALESHCHUK S.Neural networks performance in exchange rate prediction[J].Neurocomputing,2016,172(C):446-452.
[8] BEBARTA D K,SUDHA T E,BISOYI R.An intelligent stock forecasting system using a unify model of CEFLANN,HMM and GA for stock time series phenomena[C]∥Emerging Ict for Bridging the Future.Berlin:Springer-Verlag Berlin,2015:485-496.
[9] 李文鹏,高宇菲,钱佳佳,等.深度学习在量化投资中的应用[J].统计与管理,2017,9(8):104-106.
[10] HASSAN R,NATH B.Stock market forecasting using hidden Markov model:a new approach[C]∥5th International Conference on Intelligent Systems Design and Applications.Los Alamitos:IEEE,2005:192-196.
[11] PARK S H,LEE J H,SONG J W,et al.Forecasting change directions for financial time series using hidden Markov model[C]∥Rough Sets and Knowledge Technology.Berlin:Springer,2009:184-191.
[12] SEETHALAKSHMI R,KRISHNAKUMARI B,SAAVITHRI V.Gaussian kernel based HMM for time series data analysis[C]∥Conference Proceedings of 2012 International Conference on Management Issues in Emerging Economies.Thanjavur:IEEE,2012:105-109.
[13] 李腊生,翟淑萍,关敏芳.证券市场收益率分布时变性的经济学分析及其我国的经验证据[J].统计研究,2011,28(11):66-78.
[14] FIERREZ J,ORTEGA-GARCIA J,RAMOS D,et al.HMM-based on-line signature verification:feature extraction and signature modeling[J].Pattern Recognition Letters,2007,28(16):2325-2334.
[15] 肖明,贾振红.基于轮廓特征的HMM手写数字识别[J].计算机工程与应用,2010,46(33):172-174,211.
[16] CHEN F S,FU C M,HUANG C L.Hand gesture recognition using a real-time tracking method and hidden Markov models[J].Image and Vision Computing,2003,21(8):745-758.
[17] KHAN W,DAUD A,NASIR J A,et al.A survey on the state-of-the-art machine learning models in the context of NLP[J].Kuwait Journal of Science,2016,43(4):95-113.
[18] 韩普,姜杰.HMM在自然语言处理领域中的应用研究[J].计算机技术与发展,2010(2):245-248,252.
[19] PARAMONOV P,SUTULA N.Simplified scoring methods for HMM-based speech recognition[J].Soft Computing,2016,20(9):3455-3460.
[20] 谭磊.趋势跟踪类策略的内在逻辑[J].当代经济,2017,27(6):144-145.
[21] 景泰然.量化投资在期货交易中的应用[J].现代商业,2015,12(18):152-153.
[22] 张文俊,张永进.4种数据挖掘典型分类方法在股票预测中的性能分析[J].安徽工业大学学报(自然科学版),2017,34(1):97-102.

备注/Memo

备注/Memo:
收稿日期:2017-10-15 录用日期:2018-03-21
*通信作者:wuqq@xmu.edu.cn
引文格式:傅中杰,吴清强.基于隐马尔科夫模型的市场指数量化择时研究[J].厦门大学学报(自然科学版),2018,57(3):404-412.
Citation:FU Z J,WU Q Q.Research of market index quantitative timing based on hidden markov model[J].J Xiamen Univ Nat Sci,2018,57(3):404-412.(in Chinese)
更新日期/Last Update: 1900-01-01