首页> 外文会议>International conference on database and expert systems applications;DEXA 2011 >Improving Stock Market Prediction by Integrating Both Market News and Stock Prices
【24h】

Improving Stock Market Prediction by Integrating Both Market News and Stock Prices

机译:通过集成市场新闻和股票价格来改善股票市场预测

获取原文

摘要

Stock market is an important and active part of nowadays financial markets. Addressing the question as to how to model financial information from two sources, we focus on improving the accuracy of a computer aided prediction by combining information hidden in market news and stock prices in this study. Using the multi-kernel learning technique, a system is presented that makes predictions for the Hong Kong stock market by incorporating those two information sources. Experiments were conducted and the results have shown that in both cross validation and independent testing, our system has achieved better directional accuracy than those by the baseline system that is based on single one information source, as well as by the system that integrates information sources in a simple way.
机译:股票市场是当今金融市场的重要而活跃的部分。在解决有关如何从两个来源对财务信息进行建模的问题时,我们专注于通过结合隐藏在市场新闻和股票价格中的信息来提高计算机辅助预测的准确性。提出了一种使用多核学习技术的系统,通过结合这两个信息源对香港股市进行预测。进行了实验,结果表明,在交叉验证和独立测试中,我们的系统都比基于单一信息源的基线系统以及集成了单个信息源的系统获得了更好的方向精度。一种简单的方法。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号