Financial time series analysis using FWNN with robust training algorithm

Yuji Ikutake, Hiromitsu Ohmori

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Finanicial market is characterized with complex, stochastic, nonstationary process and the development of effective models for prediction of a stock price is one of the important problems in finance. For analyzing nonlinear time- series, the importance of nonlinear models, such as neural networks (NNs) and fuzzy systems (FSs), has been increasing in recent years. Combining NNs, FSs and wavelets, FuzzyWavelet Neural Network (FWNN) ,which has advantages of each systems, was devised. However, when time-series analysis is actually conducted, these time-series data are influenced by disturbance or noise. So in this paper, we introduce FWNN with robust training algorithm which can guarantee the prediction accuracy to some extent even in such a case.

Original languageEnglish
Title of host publicationProceedings of the SICE Annual Conference
Pages1199-1204
Number of pages6
Publication statusPublished - 2013
Event2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013 - Nagoya, Japan
Duration: 2013 Sep 142013 Sep 17

Other

Other2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013
CountryJapan
CityNagoya
Period13/9/1413/9/17

Fingerprint

Time series analysis
Neural networks
Fuzzy systems
Time series
Finance
Random processes

Keywords

  • Fuzzy wavelet neural networks
  • Robust training algorithm
  • Time-series analysis

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Computer Science Applications

Cite this

Ikutake, Y., & Ohmori, H. (2013). Financial time series analysis using FWNN with robust training algorithm. In Proceedings of the SICE Annual Conference (pp. 1199-1204)

Financial time series analysis using FWNN with robust training algorithm. / Ikutake, Yuji; Ohmori, Hiromitsu.

Proceedings of the SICE Annual Conference. 2013. p. 1199-1204.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ikutake, Y & Ohmori, H 2013, Financial time series analysis using FWNN with robust training algorithm. in Proceedings of the SICE Annual Conference. pp. 1199-1204, 2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013, Nagoya, Japan, 13/9/14.
Ikutake Y, Ohmori H. Financial time series analysis using FWNN with robust training algorithm. In Proceedings of the SICE Annual Conference. 2013. p. 1199-1204
Ikutake, Yuji ; Ohmori, Hiromitsu. / Financial time series analysis using FWNN with robust training algorithm. Proceedings of the SICE Annual Conference. 2013. pp. 1199-1204
@inproceedings{0dd27757cbd34ab4acf8214fb490c4a1,
title = "Financial time series analysis using FWNN with robust training algorithm",
abstract = "Finanicial market is characterized with complex, stochastic, nonstationary process and the development of effective models for prediction of a stock price is one of the important problems in finance. For analyzing nonlinear time- series, the importance of nonlinear models, such as neural networks (NNs) and fuzzy systems (FSs), has been increasing in recent years. Combining NNs, FSs and wavelets, FuzzyWavelet Neural Network (FWNN) ,which has advantages of each systems, was devised. However, when time-series analysis is actually conducted, these time-series data are influenced by disturbance or noise. So in this paper, we introduce FWNN with robust training algorithm which can guarantee the prediction accuracy to some extent even in such a case.",
keywords = "Fuzzy wavelet neural networks, Robust training algorithm, Time-series analysis",
author = "Yuji Ikutake and Hiromitsu Ohmori",
year = "2013",
language = "English",
pages = "1199--1204",
booktitle = "Proceedings of the SICE Annual Conference",

}

TY - GEN

T1 - Financial time series analysis using FWNN with robust training algorithm

AU - Ikutake, Yuji

AU - Ohmori, Hiromitsu

PY - 2013

Y1 - 2013

N2 - Finanicial market is characterized with complex, stochastic, nonstationary process and the development of effective models for prediction of a stock price is one of the important problems in finance. For analyzing nonlinear time- series, the importance of nonlinear models, such as neural networks (NNs) and fuzzy systems (FSs), has been increasing in recent years. Combining NNs, FSs and wavelets, FuzzyWavelet Neural Network (FWNN) ,which has advantages of each systems, was devised. However, when time-series analysis is actually conducted, these time-series data are influenced by disturbance or noise. So in this paper, we introduce FWNN with robust training algorithm which can guarantee the prediction accuracy to some extent even in such a case.

AB - Finanicial market is characterized with complex, stochastic, nonstationary process and the development of effective models for prediction of a stock price is one of the important problems in finance. For analyzing nonlinear time- series, the importance of nonlinear models, such as neural networks (NNs) and fuzzy systems (FSs), has been increasing in recent years. Combining NNs, FSs and wavelets, FuzzyWavelet Neural Network (FWNN) ,which has advantages of each systems, was devised. However, when time-series analysis is actually conducted, these time-series data are influenced by disturbance or noise. So in this paper, we introduce FWNN with robust training algorithm which can guarantee the prediction accuracy to some extent even in such a case.

KW - Fuzzy wavelet neural networks

KW - Robust training algorithm

KW - Time-series analysis

UR - http://www.scopus.com/inward/record.url?scp=84888615127&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84888615127&partnerID=8YFLogxK

M3 - Conference contribution

SP - 1199

EP - 1204

BT - Proceedings of the SICE Annual Conference

ER -