Presentation 1997/3/18
Stock Exchange Analysis as Time-Series Forecasting with Neural Nets
Alexandra Ioana Cristea, Toshio Okamoto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Stock Exchange Events(SEE)as Time-Series(TS)present the typical components of TS: Trend, Cyclus, Season, Irregular events. Neural Networks(NN)can be used as a tool to forecast SEE, at the level of three of the four components mentioned. The forth component requires an experience-based, therefore economy based learning method. Testing is performed by a program. Input data are: stock market prices, previously aquired information in form of a weights matrix, or new prices on the stock market. This 3-level hierarchy serves for the 3steps: training, testing, prediction. Current results will be presented and, as much as possible, comparison with former systems performed.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Neural Computing / Neural Networks / Stock Exchange / Time Series
Paper # AI96-44,KBSE96-34
Date of Issue

Conference Information
Committee AI
Conference Date 1997/3/18(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Artificial Intelligence and Knowledge-Based Processing (AI)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Stock Exchange Analysis as Time-Series Forecasting with Neural Nets
Sub Title (in English)
Keyword(1) Neural Computing
Keyword(2) Neural Networks
Keyword(3) Stock Exchange
Keyword(4) Time Series
1st Author's Name Alexandra Ioana Cristea
1st Author's Affiliation The Graduate School of Information Systems,University of Electro-Commnnications()
2nd Author's Name Toshio Okamoto
2nd Author's Affiliation The Graduate School of Information Systems,University of Electro-Commnnications
Date 1997/3/18
Paper # AI96-44,KBSE96-34
Volume (vol) vol.96
Number (no) 594
Page pp.pp.-
#Pages 8
Date of Issue