珞珈金融论坛(第56期)
发布日期:2016-12-15 20:37:02  点击量:

题目:Stock Market Prediction Using Weighted Inter-Transaction Class Association Rule Mining and Evolutionary Algorithm

报告人:陈艳,上海财经大学统计与管理学院副教授、博士生导师,金融统计与风险管理系主任

时间:2016年12月22日(周四) 15:00 ~ 16:30

地点:经管院B226

 

报告摘要如下:

  Evolutionary computation and data mining are two interesting fields which attract many researchers. In this paper, a new rule mining method is proposed to solve the prediction problem based on the evolutionary algorithm named genetic network programming. Compared with the traditional methods, the proposed algorithm has been proved to have many advantages for the financial prediction, since it is able to find the relationships among attributes from different transactions. Experimental results on the New York Exchange Market show that the new method outperforms other conventional models in terms of both accuracy and profitability, which uses the relationship between stock prices and volumes as the weight of rules. It is clarified that the proposed data mining method is effective for the prediction in the financial market.

 

报告人简介:

  陈艳,日本早稻田大学工学博士,上海财经大学统计与管理学院副教授,博士生导师,金融统计与风险管理系主任,上海市“浦江人才计划”入选者,上海市“晨光学者计划”入选者,“中国优选法统筹法与经济数学研究会”理事。陈艳博士长期从事金融统计与管理科学的研究工作,研究领域包括量化投资、风险管理与机器学习等,主要致力于智能交易系统的构建及其在金融预测与风险管理方面的应用研究。先后担任日本学术振兴会(JSPS)研究员、早稻田大学客座研究员。在科研方面,陈艳博士在金融预测和智能系统的建立等方面取得了一系列成果,先后主持并完成国家自然科学基金项目2项,省部级项目3项,在国内外核心期刊《European Journal of Operational Research》、《Computer and Operations Research》等发表学术论文20余篇。多次应邀参加国际一流学术会议IEEE SMC、GECCO、CEC、WCCI等并做学术报告,长期担任分会主席及组委会成员,参与编写《Machine Learning》著作一部,曾获多项科研成果奖。