摘要
采用稳健的改进主成分分析与支持向量机(PCA-SVM)算法进行特征提取,分析中国股票市场的股票选择问题,并采用中国沪、深A股市场中上市公司数据验证该方法的有效性.结果表明,运用PCA-SVM算法得到的组合回报率超过了市场基准.
Selecting stocks in China s stock market was researched using a classification method of support vector machine（SVM） and robust and improved method of PCA for feature extraction.Using the data of listed companies of China A stocks market experiments were done to test the validity of the method mentioned above.The result indicates that portfolio s return rate using classification method of SVM is higher than the market benchmark.
出处
《上海交通大学学报》
EI
CAS
CSCD
北大核心
2009年第9期1412-1416,共5页
Journal of Shanghai Jiaotong University
关键词
支持向量机
分类算法
特征提取
股票选择
回报率
support vector machine（SVM）
classification algorithm
feature extraction
stock selection
return rate
