Presentation 2015-06-05
Stock market prediction from Web news using filtering and machine learning
Ko Ichinose, Kazutaka Shimada,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The market analysis is one of the important tasks for text mining. Many researchers have proposed methods using text information for analyzing the market. In this situation, Web news have the important role to predict stock prices. In this paper, we propose a method to predict the Nikkei Stock Average, which is one of the most important stock market indexes. We apply a filtering process and a machine learning into the method. First, we select important news from many Web news by using the filtering. Then, we classify the selected news into``UP" and``Down" by using a machine learning method. Finally, we predict the change of the next day's Nikkei stock price. The experimental result shows the effectiveness of the filtering process for the Web news based classification task.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Web-news / Stock price prediction / filtering / SVM
Paper # TL2015-16,NLC2015-16
Date of Issue 2015-05-28 (TL, NLC)

Conference Information
Committee NLC / TL
Conference Date 2015/6/4(2days)
Place (in Japanese) (See Japanese page)
Place (in English) The University of Tokushima
Topics (in Japanese) (See Japanese page)
Topics (in English) Application of natural language proessing and linguistic analysis, and general topic of NLP
Chair Koichi Takeuchi(Okayama Univ.) / Tadahisa Kondo(Kogakuin Univ.)
Vice Chair Hiroshi Kanayama(IBM) / Makoto Ichise(NTT DoCoMo) / Chiaki Kubomura(Yamano College of Aesthetics) / Masami Suzuki(KDDI R&D Labs.)
Secretary Hiroshi Kanayama(Univ. of Tokyo/Hottolink) / Makoto Ichise(Ryukoku Univ.) / Chiaki Kubomura(Univ. of Tsukuba) / Masami Suzuki(Kyorin Univ.)
Assistant Kazutaka Shimada(Kyushu Inst. of Tech.) / Ryuichiro Higashinaka(NTT) / Eiji Tomida(Ehime Univ.) / Yasushi Tsubota(Kyoto Univ.)

Paper Information
Registration To Technical Committee on Natural Language Understanding and Models of Communication / Technical Committee on Thought and Language
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Stock market prediction from Web news using filtering and machine learning
Sub Title (in English)
Keyword(1) Web-news
Keyword(2) Stock price prediction
Keyword(3) filtering
Keyword(4) SVM
1st Author's Name Ko Ichinose
1st Author's Affiliation Kyushu Institute of Technology(KIT)
2nd Author's Name Kazutaka Shimada
2nd Author's Affiliation Kyushu Institute of Technology(KIT)
Date 2015-06-05
Paper # TL2015-16,NLC2015-16
Volume (vol) vol.115
Number (no) TL-69,NLC-70
Page pp.pp.91-96(TL), pp.91-96(NLC),
#Pages 6
Date of Issue 2015-05-28 (TL, NLC)