XCS分类元系统于金融投资决策上之应用——以台湾加权指数为例

Application of XCS Classifier System to Financial Decision Support:An Empirical Study of TAIEX

人工智能模型近年来在财经领域上的应用相当广泛,也常与传统的统计模型相互比较。传统时间序列数学模型存在许多假设与限制,但人工智能模型较具有弹性,可解决非线性问题,较适合应用于像股票市场这种动态环境。该研究为应用人工智能方法之分类元系统(classifiersys-tem,CS)模型于台湾加权指数趋势之预测。分类元是一种以基因算法为基础的学习模式。它拥有一个规则集,而且会动态对环境进行调整。该研究运用不同天期移动平均线(MA)、随机指针(KD)、平滑异同移动平均线(MACD)等技术指针当作输入因子,加权指数之买卖讯号作为输出因子,经由分类元系统动态学习买卖规则,每次操作以加权指数为交易标的。实证结果显示10年测试期间分类元股票交易系统(CSTS)30次仿真结果之平均报酬率为165·38%,平均交易胜率为60·31%。统计分析显示CSTS系统之平均交易报酬率及交易准确率皆显著优于传统回归模式及随机交易策略。证实分类元系统可较传统策略准确掌握加权指数之趋势,非常适合投资者作为交易决策系统。

Stock market is nonlinear and semi-structured. In Taiwan, stock market is always affected by political factors. So the fluctuation of stock price is always larger than other country. Therefore, to predict the trend of stock index is more important. Traditional trading strategy, such as regression model and random walk are limited in fixed time interval and can not perform well. Other learning models, such as genetic algorithms, result in stable trading rules which are generated from specific training time period without being adapted when the environment state is changed. This paper adopted Extended Classifier System(XCS) technique to design a XCS-based security trading system(CSTS), which makes continuous on-line learning while making decision and generate trading rules to adapt environment state. The simulation results showed that this system could get an outstanding trading profit and accuracy rate.