版权说明 帮助中心
首页 > 成果 > 详情

LG-Trader: Stock trading decision support based on feature selection by weighted localized generalization error model

SCI-EEI
WOS被引频次:4
认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Ng, Wing W.Y.;Liang, Xue-Ling;Li, Jincheng*;Yeung, Daniel S.;Chan, Patrick P.K.
通讯作者:
Li, Jincheng
作者机构:
[Liang, Xue-Ling; Chan, Patrick P.K.; Ng, Wing W.Y.; Yeung, Daniel S.; Li, Jincheng] Machine Learning and Cybernetic Research Center, School of Computer Science and Engineering, South China University of Technology, Guangzhou, China
[Li, Jincheng] College of Medical Information Engineering, Guangdong Pharmaceutical University, Guangzhou 510006, China
通讯机构:
[Li, Jincheng] S China Univ Technol, Machine Learning & Cybernet Res Ctr, Sch Engn & Comp Sci, Guangzhou, Guangdong, Peoples R China.
语种:
英文
关键词:
LG-Trader - Localized generalization error models - Localized generalization errors - Machine learning research - Machine learning techniques - MLPNN - Multi objective - Stock trading
期刊:
Neurocomputing
ISSN:
0925-2312
年:
2014
卷:
146
页码:
104-112
文献类别:
WOS:Article;EI:Journal article (JA)
所属学科:
ESI学科类别:计算机科学;WOS学科类别:Computer Science, Artificial Intelligence
入藏号:
WOS:000342529500010;EI:20143618144122
基金类别:
National Natural Science Foundation of China [61003171, 61272201, 61003172]; Program for New Century Excellent Talents in University of China [NCET-11-0162]
机构署名:
本校为其他机构
院系归属:
医药信息工程学院
摘要:
Stock trading is an important financial activity of human society. Machine learning techniques are adopted to provide trading decision support by predicting the stock price or trading signals of the next day. Decisions are made by analyzing technical indices and fundamental analysis of companies. There are two major machine learning research problems for stock trading decision support: classifier architecture selection and feature selection. In this work, we propose the LG-Trader which will deal with these two problems simultaneously using a genetic algorithm minimizing a new Weighted Localized Generalization Error (wL-GEM). An issue being ignored in current machine learning based stock trading researches is the imbalance among buy, hold and sell decisions. Usually hold decision is the majority in comparison to both buy and sell decisions. So, the wL-GEM is proposed to balance classes by penalizing heavier for generalization error being made in minority classes. The feature selection based on wL-GEM helps to select most useful technical indices among choices for each stock. Experimental results demonstrate that the LG-Trader yields higher profits and rates of return in both stock and index trading. ©2014 Elsevier B.V.
参考文献:
Yu L, 2009, IEEE T EVOLUT COMPUT, V13, P87, DOI 10.1109/TEVC.2008.928176
Yeung DS, 2007, J SYST SCI SYST ENG, V16, P166, DOI 10.1007/s11518-007-5048-4
Lee JW, 2007, IEEE T SYST MAN CY A, V37, P864, DOI 10.1109/TSMCA.2007.904825
Lu CJ, 2010, EXPERT SYST APPL, V37, P7056, DOI 10.1016/j.eswa.2010.03.012
Yeung DS, 2007, IEEE T NEURAL NETWOR, V18, P1294, DOI 10.1109/TNN.2007.894058

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com