An evolutionary trend reversion model for stock trading rule discovery
An evolutionary trend reversion model for stock trading rule discovery
复制标题
股票交易规则发现的演化趋势回归模型
DOI：
10.1016/j.knosys.2014.08.010
复制
发表时间：
2015-05
影响因子：
8.8
通讯作者：
Mei Liu
中科院分区：
文献类型：
--
作者：
Kang Xie;Weiguo Zhang;Lijun Su;Mei Liu
量化投资（QI）无疑是大数据分析中的一个热门话题。扩展分类器系统（XCS）由于其固有的分类规则挖掘、进化学习和强化学习等技术，具有良好的学习能力和显式表达能力，非常适合在海量、复杂、非线性的股票市场数据中进行知识发现。本文提出了一种进化趋势反转模型（eTrendRev），它是基于所提出的XCS与学习模式（XCSL）和趋势反转策略。eTrendRev在三个方面有突出的表现：（1）XCSL生成的显式规则比黑盒模型（如神经网络）更容易理解，从而可以提供合理的知识来指导交易;（2）XCS的原始纯探索模型被提出的learn模型所取代，在本研究中表现出更好的性能和更稳定的性能;（3）通过进化学习，将各种趋势逆转策略整合并动态化。在模型评价方面，利用上证综合指数和纳斯达克综合指数的历史数据进行了实验，回测结果表明，eTrendRev能够以较低的风险获得较高的收益，并能够及时识别重大的市场转折点。这项研究还证实了在基于机器学习的QI模型中使用唯一趋势逆转指标的盈利能力。
Quantitative investment (QI) is certainly a hot topic in big data analysis. For knowledge discovery in huge, complex and nonlinear stock market data, the eXtended Classifier Systems (XCS) is quite suitable because of the excellent learning and explicit expression abilities derived from its intrinsic techniques that include classification rule mining, evolutionary learning and reinforcement learning. This paper presents an Evolutionary Trend Reversion Model (eTrendRev), which is based on the proposed XCS withlearnmode (XCSL) and trend-reversion strategy. The eTrendRev is highlighted in three aspects: (1) the explicit rules generated by XCSL are more understandable than black-box models, such as neural networks, thus can provide justifiable knowledge to guide trading; (2) the originalpure exploremode of XCS is substituted by the proposedlearnmode, which is shown in this study to perform better and is more stable; (3) a variety of trend-reversion strategies are integrated and made dynamic through evolutionary learning. For model evaluation, experiments were carried out on the historical data of the Shanghai Composite Index and the NASDAQ Composite Index, and back-testing results indicate that eTrendRev can produce higher return with lower risk and recognize significant market turning points in a timely fashion. This study also confirms the profitability of using sole trend-reversion indicators in machine learning-based QI model.
登录
查看更多内容
影响因子：
7.5
作者：
Lam, M
通讯作者：
Lam, M
DOI：
10.1142/s0219622006001824
发表时间：
2006-03
期刊：
Int. J. Inf. Technol. Decis. Mak.
影响因子：
--
作者：
Na Ren;M. Zargham;S. Rahimi
通讯作者：
Na Ren;M. Zargham;S. Rahimi
DOI：
10.1016/j.engappai.2013.04.004
发表时间：
2013-09
期刊：
Eng. Appl. Artif. Intell.
影响因子：
--
作者：
M. Shariat Panahi;A. Yousefi;M. Khorshidi
通讯作者：
M. Shariat Panahi;A. Yousefi;M. Khorshidi
DOI：
10.1016/j.knosys.2006.05.011
发表时间：
2005-11
期刊：
2005 International Conference on Machine Learning and Cybernetics
影响因子：
--
作者：
Jinmao Wei;Wei-Guo Yi;Ming-Yang Wang
通讯作者：
Jinmao Wei;Wei-Guo Yi;Ming-Yang Wang
DOI：
10.1016/j.dss.2013.01.019
发表时间：
2013-04
期刊：
Decis. Support Syst.
影响因子：
--
作者：
D. A. Gaines;Ramakrishnan Pakath
通讯作者：
D. A. Gaines;Ramakrishnan Pakath