Artificial neural networks for non-stationary time series

Tae Yoon Kim; Kyong Joo Oh; Chiho Kim; Jong Doo Do

doi:10.1016/j.neucom.2004.04.002

Artificial neural networks for non-stationary time series

Tae Yoon Kim, Kyong Joo Oh, Chiho Kim, Jong Doo Do

Department of Industrial Engineering

Research output: Contribution to journal › Article › peer-review

83 Citations (Scopus)

Abstract

The use of artificial neural networks (ANN) has received increasing attention in the analysis and prediction of financial time series. Stationarity of the observed financial time series is the basic underlying assumption in the practical application of ANN on financial time series. In this paper, we will investigate whether it is feasible to relax the stationarity condition to non-stationary time series. Our result discusses the range of complexities caused by non-stationary behavior and finds that overfitting by ANN could be useful in the analysis of such non-stationary complex financial time series.

Original language	English
Pages (from-to)	439-447
Number of pages	9
Journal	Neurocomputing
Volume	61
Issue number	1-4
DOIs	https://doi.org/10.1016/j.neucom.2004.04.002
Publication status	Published - 2004 Oct

Bibliographical note

Funding Information:
This research is supported by Korea Research Foundation Grant 2003-070-C00008. We are very grateful to the anonymous referees for their careful review.

All Science Journal Classification (ASJC) codes

Computer Science Applications
Cognitive Neuroscience
Artificial Intelligence

Access to Document

10.1016/j.neucom.2004.04.002

Cite this

@article{29026f30cf3f4fadbdcb97ff6887c02d,

title = "Artificial neural networks for non-stationary time series",

abstract = "The use of artificial neural networks (ANN) has received increasing attention in the analysis and prediction of financial time series. Stationarity of the observed financial time series is the basic underlying assumption in the practical application of ANN on financial time series. In this paper, we will investigate whether it is feasible to relax the stationarity condition to non-stationary time series. Our result discusses the range of complexities caused by non-stationary behavior and finds that overfitting by ANN could be useful in the analysis of such non-stationary complex financial time series.",

author = "Kim, {Tae Yoon} and Oh, {Kyong Joo} and Chiho Kim and Do, {Jong Doo}",

note = "Funding Information: This research is supported by Korea Research Foundation Grant 2003-070-C00008. We are very grateful to the anonymous referees for their careful review.",

year = "2004",

month = oct,

doi = "10.1016/j.neucom.2004.04.002",

language = "English",

volume = "61",

pages = "439--447",

journal = "Neurocomputing",

issn = "0925-2312",

publisher = "Academic Press Inc.",

number = "1-4",

}

TY - JOUR

T1 - Artificial neural networks for non-stationary time series

AU - Kim, Tae Yoon

AU - Oh, Kyong Joo

AU - Kim, Chiho

AU - Do, Jong Doo

N1 - Funding Information: This research is supported by Korea Research Foundation Grant 2003-070-C00008. We are very grateful to the anonymous referees for their careful review.

PY - 2004/10

Y1 - 2004/10

N2 - The use of artificial neural networks (ANN) has received increasing attention in the analysis and prediction of financial time series. Stationarity of the observed financial time series is the basic underlying assumption in the practical application of ANN on financial time series. In this paper, we will investigate whether it is feasible to relax the stationarity condition to non-stationary time series. Our result discusses the range of complexities caused by non-stationary behavior and finds that overfitting by ANN could be useful in the analysis of such non-stationary complex financial time series.

AB - The use of artificial neural networks (ANN) has received increasing attention in the analysis and prediction of financial time series. Stationarity of the observed financial time series is the basic underlying assumption in the practical application of ANN on financial time series. In this paper, we will investigate whether it is feasible to relax the stationarity condition to non-stationary time series. Our result discusses the range of complexities caused by non-stationary behavior and finds that overfitting by ANN could be useful in the analysis of such non-stationary complex financial time series.

UR - http://www.scopus.com/inward/record.url?scp=10244222718&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=10244222718&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2004.04.002

DO - 10.1016/j.neucom.2004.04.002

M3 - Article

AN - SCOPUS:10244222718

SN - 0925-2312

VL - 61

SP - 439

EP - 447

JO - Neurocomputing

JF - Neurocomputing

IS - 1-4

ER -

Artificial neural networks for non-stationary time series

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this