Stochastic variance models in discrete time with feedforward neural networks

Charles Andoh

doi:10.1162/neco.2009.11-07-642

Stochastic variance models in discrete time with feedforward neural networks

Charles Andoh

University of Ghana Business School

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

3 Citations (Scopus)

Abstract

The study overcomes the estimation difficulty in stochastic variance mod- els for discrete financial time series with feedforward neural networks. The volatility function is estimated semiparametrically. The model is used to estimate market risk, taking into account not only the time se- ries of interest but extra information on the market. As an application, some stock prices series are studied and compared with the nonlinear ARX-ARCHX model.

Original language	English
Pages (from-to)	1990-2008
Number of pages	19
Journal	Neural Computation
Volume	21
Issue number	7
DOIs	https://doi.org/10.1162/neco.2009.11-07-642
Publication status	Published - Jul 2009
Externally published	Yes

Access to Document

10.1162/neco.2009.11-07-642

Cite this

@article{844318a14039407aa7b64981f3c8304d,

title = "Stochastic variance models in discrete time with feedforward neural networks",

abstract = "The study overcomes the estimation difficulty in stochastic variance mod- els for discrete financial time series with feedforward neural networks. The volatility function is estimated semiparametrically. The model is used to estimate market risk, taking into account not only the time se- ries of interest but extra information on the market. As an application, some stock prices series are studied and compared with the nonlinear ARX-ARCHX model.",

author = "Charles Andoh",

year = "2009",

month = jul,

doi = "10.1162/neco.2009.11-07-642",

language = "English",

volume = "21",

pages = "1990--2008",

journal = "Neural Computation",

issn = "0899-7667",

publisher = "MIT Press Journals",

number = "7",

}

TY - JOUR

T1 - Stochastic variance models in discrete time with feedforward neural networks

AU - Andoh, Charles

PY - 2009/7

Y1 - 2009/7

N2 - The study overcomes the estimation difficulty in stochastic variance mod- els for discrete financial time series with feedforward neural networks. The volatility function is estimated semiparametrically. The model is used to estimate market risk, taking into account not only the time se- ries of interest but extra information on the market. As an application, some stock prices series are studied and compared with the nonlinear ARX-ARCHX model.

AB - The study overcomes the estimation difficulty in stochastic variance mod- els for discrete financial time series with feedforward neural networks. The volatility function is estimated semiparametrically. The model is used to estimate market risk, taking into account not only the time se- ries of interest but extra information on the market. As an application, some stock prices series are studied and compared with the nonlinear ARX-ARCHX model.

UR - http://www.scopus.com/inward/record.url?scp=68349132126&partnerID=8YFLogxK

U2 - 10.1162/neco.2009.11-07-642

DO - 10.1162/neco.2009.11-07-642

M3 - Letter

C2 - 19323636

AN - SCOPUS:68349132126

SN - 0899-7667

VL - 21

SP - 1990

EP - 2008

JO - Neural Computation

JF - Neural Computation

IS - 7

ER -

Stochastic variance models in discrete time with feedforward neural networks

Abstract

Access to Document

Other files and links

Fingerprint

Cite this