Using Extended Classifier System for Portfolio Allocation of MSCI Index Component Stocks

2009 Fifth International Joint Conference on INC, IMS and IDC Pub Date : 2009-08-25 DOI:10.1109/NCM.2009.388

Wen-Chih Tsai, Chiung-Fen Huang, An-Pin Chen

{"title":"Using Extended Classifier System for Portfolio Allocation of MSCI Index Component Stocks","authors":"Wen-Chih Tsai, Chiung-Fen Huang, An-Pin Chen","doi":"10.1109/NCM.2009.388","DOIUrl":null,"url":null,"abstract":"In a recent study, Lin [11] proposed the LCS for short-term stock forecast. Gershoff [13] proposed the extended Classifier system (XCS) agent to model different traders by supplying different input information. Announcement made by Morgan Stanley Capital Investment (MSCI) regarding the additions, removals, and even the weights of the component stocks in its country indices every quarter generally would cause changes to the prices and/or trade volumes of the associated component stocks. This paper takes an XCS in artificial intelligence to dynamically learn and adapt to the changes to the component stocks in order to optimize portfolio allocation of the component stocks. Since these price trends of MSCI component stocks are influenced by unknown and unpredictable surroundings, using XCS to model the fluctuations on financial market allows for the capability to discover the patterns of future trends. This simulation work on the basis of the changes to 121 component stocks in the MSCI Taiwan index between 1998 and 2009 suggests the XCS can produce the great profit and optimize portfolio allocation.","PeriodicalId":119669,"journal":{"name":"2009 Fifth International Joint Conference on INC, IMS and IDC","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2009-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2009 Fifth International Joint Conference on INC, IMS and IDC","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NCM.2009.388","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

In a recent study, Lin [11] proposed the LCS for short-term stock forecast. Gershoff [13] proposed the extended Classifier system (XCS) agent to model different traders by supplying different input information. Announcement made by Morgan Stanley Capital Investment (MSCI) regarding the additions, removals, and even the weights of the component stocks in its country indices every quarter generally would cause changes to the prices and/or trade volumes of the associated component stocks. This paper takes an XCS in artificial intelligence to dynamically learn and adapt to the changes to the component stocks in order to optimize portfolio allocation of the component stocks. Since these price trends of MSCI component stocks are influenced by unknown and unpredictable surroundings, using XCS to model the fluctuations on financial market allows for the capability to discover the patterns of future trends. This simulation work on the basis of the changes to 121 component stocks in the MSCI Taiwan index between 1998 and 2009 suggests the XCS can produce the great profit and optimize portfolio allocation.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

基于扩展分类系统的MSCI指数成分股组合配置

在最近的一项研究中，Lin[11]提出了LCS用于短期股票预测。Gershoff[13]提出了扩展分类器系统(XCS)代理，通过提供不同的输入信息对不同的交易者建模。摩根士丹利资本投资公司(MSCI)每季度就其国家指数中成分股的增减甚至权重作出的公告，通常会导致相关成分股的价格和/或交易量发生变化。本文采用人工智能中的XCS来动态学习和适应成分股的变化，以优化成分股的投资组合配置。由于MSCI成分股的这些价格趋势受到未知和不可预测的环境的影响，使用XCS对金融市场的波动进行建模，可以发现未来趋势的模式。通过对MSCI台湾指数中121只成分股1998 ~ 2009年的变动情况进行模拟，结果表明XCS能够产生较大的收益，优化组合配置。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

2009 Fifth International Joint Conference on INC, IMS and IDC

自引率

0.00%

发文量

期刊最新文献

Based on Improved BP Neural Network to Forecast Demand for Spare Parts Integrated Network Management Certification Training with Computer Game: A Knowledge Placement Framework Improving Scalability for RFID Privacy Protection Using Parallelism A Brand-New Mobile Value-Added Service: M-Check A Uniform Construction of New Exact Travelling Wave Solutions and its Applications