An empirical methodology for developing stockmarket trading systems using artificial neural networks

Bruce Vanstone, Gavin Finnie

Research output: Contribution to journalArticleResearchpeer-review

58 Citations (Scopus)
42 Downloads (Pure)

Abstract

A great deal of work has been published over the past decade on the application of neural networks to stockmarket trading. Individual researchers have developed their own techniques for designing and testing these neural networks, and this presents a difficulty when trying to learn lessons and compare results. This paper aims to present a methodology for designing robust mechanical trading systems using soft computing technologies, such as artificial neural networks. This paper describes the key steps involved in creating a neural network for use in stockmarket trading, and places particular emphasis on designing these steps to suit the real-world constraints the neural network will eventually operate in. Such a common methodology brings with it a transparency and clarity that should ensure that previously published results are both reliable and reusable.

Original languageEnglish
Pages (from-to)6668-6680
Number of pages13
JournalExpert Systems with Applications
Volume36
Issue number3 PART 2
DOIs
Publication statusPublished - Apr 2009

Fingerprint

Neural networks
Soft computing
Transparency
Testing

Cite this

@article{b819bd4c31d24b039885e989ab013b39,
title = "An empirical methodology for developing stockmarket trading systems using artificial neural networks",
abstract = "A great deal of work has been published over the past decade on the application of neural networks to stockmarket trading. Individual researchers have developed their own techniques for designing and testing these neural networks, and this presents a difficulty when trying to learn lessons and compare results. This paper aims to present a methodology for designing robust mechanical trading systems using soft computing technologies, such as artificial neural networks. This paper describes the key steps involved in creating a neural network for use in stockmarket trading, and places particular emphasis on designing these steps to suit the real-world constraints the neural network will eventually operate in. Such a common methodology brings with it a transparency and clarity that should ensure that previously published results are both reliable and reusable.",
author = "Bruce Vanstone and Gavin Finnie",
year = "2009",
month = "4",
doi = "10.1016/j.eswa.2008.08.019",
language = "English",
volume = "36",
pages = "6668--6680",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier",
number = "3 PART 2",

}

An empirical methodology for developing stockmarket trading systems using artificial neural networks. / Vanstone, Bruce; Finnie, Gavin.

In: Expert Systems with Applications, Vol. 36, No. 3 PART 2, 04.2009, p. 6668-6680.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - An empirical methodology for developing stockmarket trading systems using artificial neural networks

AU - Vanstone, Bruce

AU - Finnie, Gavin

PY - 2009/4

Y1 - 2009/4

N2 - A great deal of work has been published over the past decade on the application of neural networks to stockmarket trading. Individual researchers have developed their own techniques for designing and testing these neural networks, and this presents a difficulty when trying to learn lessons and compare results. This paper aims to present a methodology for designing robust mechanical trading systems using soft computing technologies, such as artificial neural networks. This paper describes the key steps involved in creating a neural network for use in stockmarket trading, and places particular emphasis on designing these steps to suit the real-world constraints the neural network will eventually operate in. Such a common methodology brings with it a transparency and clarity that should ensure that previously published results are both reliable and reusable.

AB - A great deal of work has been published over the past decade on the application of neural networks to stockmarket trading. Individual researchers have developed their own techniques for designing and testing these neural networks, and this presents a difficulty when trying to learn lessons and compare results. This paper aims to present a methodology for designing robust mechanical trading systems using soft computing technologies, such as artificial neural networks. This paper describes the key steps involved in creating a neural network for use in stockmarket trading, and places particular emphasis on designing these steps to suit the real-world constraints the neural network will eventually operate in. Such a common methodology brings with it a transparency and clarity that should ensure that previously published results are both reliable and reusable.

UR - http://www.scopus.com/inward/record.url?scp=58349093897&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2008.08.019

DO - 10.1016/j.eswa.2008.08.019

M3 - Article

VL - 36

SP - 6668

EP - 6680

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 3 PART 2

ER -