摘要
股票市场的预测一直是数据研究热点,但是受到很多因素的影响,其预测难度较高.新闻是影响股价的重要因素,投资者也经常依赖新闻进行股票交易与决策,因此对新闻的剖析可以为投资者提供有效信息.新闻作为非结构性数据运用到股票预测中困难重重,而随着机器学习技术和自然语言分析技术的发展,使得该问题的解决成为了可能.目前国内外资本市场政策上的显著差异性导致越来越多的国内企业在国外上市,而关于中文新闻对中概股预测影响的研究却很少.本文提出了一种新的循环评估支持向量机(Cyclic Evaluation Support Vector Machine,CE-SVM)模型,并将其应用于新闻极性对中概股预测的研究中.实验证明,CE-SVM相比起朴素贝叶斯模型提高了4%的准确率,证明了方法的有效性.
Stock market prediction has always been a hot topic in data research,but it is difficult to predict due to the influence of many factors. News is an important factor affecting stock price,and investors often rely on news for stock trading and decision-making.Therefore,the analysis of news can provide investors with effective information. However,the application of news as unstructured data to stock forecasting is difficult. With the development of machine learning and natural language analysis,it is possible to solve this problem. The significant difference in domestic and foreign capital market policies leads to more domestic enterprises listing in foreign countries,but there are few studies on the influence of news on Chinese concept stocks. A new Cyclic Evaluation Support Vector Machine(CE-SVM) model was proposed in this paper,and applied to the research of forecasting Chinese concept stocks by news polarity.Experiments show that CE-SVM improves the accuracy by 4% compared with the Naive Bayesian model,which proves the effectiveness of the method.
作者
赵澄
童川
王万良
ZHAO Cheng;TONG Chuan;WANG Wan-liang(College of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310023,China)
出处
《小型微型计算机系统》
CSCD
北大核心
2020年第3期526-531,共6页
Journal of Chinese Computer Systems
基金
国家自然科学基金项目(61902349)资助.
关键词
新闻
股票预测
CE-SVM
极性
中概股
news
stock prediction
CE-SVM
polarity
Chinese concept stocks