中文摘要：

近年来股票市场预测研究一直较受欢迎。大量研究者尝试基于多种数学模型的技术指数及机器学习技术预测股票价格或指数。尽管现有方法展示了较满意的预测成就,但是股票市场是升还是降的预测准确性很少被分析。用Wrap-per方法从由23个技术指标构成的原始特征集中选择最优特征子集,然后用混合不同分类算法的投票法来预测两股票市场的趋势。实验结果表明Wrapper方法比常用的Filter式特征选择算法如χ^2-统计,信息增益,Relief F,对称不确定性,和CFS能有更好的性能。此外,提出的投票法超越单一的分类器如SVM,K最邻近,BP神经网络,决策树和Logistic回归。

英文摘要：

The research on the stock market prediction has been more popular in recent years.Numerous researchers tried to predict stock prices or indices based on technical indices with various mathematical models and machine learning techniques.Although these researches exhibit satisfactory prediction accuracy,the prediction accuracy of whether stock market goes or down is seldom analyzed.Employ Wrapper approach to select the optimal feature subset from original feature set composed of 23 technical indices and then use voting scheme that combines different classification algorithms to predict the trend in stock markets. Experimental result shows that Wrapper approach can achieve better performance than the commonly used feature filters, such as X^2 - statistic, information gain, ReliefF, symmetrical uncertainty and CFS. Moreover, the proposed voting scheme outperforms single classifier such as SVM,kth nearest neighbor, hack- propagation neural network, decision tree, and logistic regression.