Presentation 2000/3/14
A selection method of learning data for nonstationary time series prediction
Satoshi Tsuji, Nobuhiko Ogura, Sumio Watanabe,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a selection method of optimal learning data for the prediction of time series data with nonstationary factors. In case of prediction of time series data produced from the changing environment, there are useless data in all of the past data for the presumption of the most suitable parameters to the present environment. So we aim at more superior prediction by the selection of data. We evaluate this method with the daily exchange rate between Japanese yen and U.S.dollar. As a result, we can attest to the effectiveness of this method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) nonstationary time series / method of least-squares / mean square error
Paper # NC99-121
Date of Issue

Conference Information
Committee NC
Conference Date 2000/3/14(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A selection method of learning data for nonstationary time series prediction
Sub Title (in English)
Keyword(1) nonstationary time series
Keyword(2) method of least-squares
Keyword(3) mean square error
1st Author's Name Satoshi Tsuji
1st Author's Affiliation Precision and Intelligence Laboratory Tokyo Institute of Technology()
2nd Author's Name Nobuhiko Ogura
2nd Author's Affiliation Precision and Intelligence Laboratory Tokyo Institute of Technology
3rd Author's Name Sumio Watanabe
3rd Author's Affiliation Precision and Intelligence Laboratory Tokyo Institute of Technology
Date 2000/3/14
Paper # NC99-121
Volume (vol) vol.99
Number (no) 685
Page pp.pp.-
#Pages 8
Date of Issue