Robustness test of genetic algorithm on generating rules for currency trading

Shangkun Deng, Yizhou Sun, Akito Sakurai

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

4 Citations (Scopus)

Abstract

In trading in currency markets, reducing the mean of absolute or squared errors of predicted values is not valuable unless it results in profits. A trading rule is a set of conditions that describe when to buy or sell a currency or to close a position, which can be used for automated trading. To optimize the rule to obtain a profit in the future, a probabilistic method such as a genetic algorithm (GA) or genetic programming (GP) is utilized, since the profit is a discrete and multimodal function with many parameters. Although the rules optimized by GA/GP reportedly obtain a profit in out-of-sample testing periods, it is hard to believe that they yield a profit in distant out-of-sample periods. In this paper, we first consider a framework where we optimize the parameters of the trading rule in an in-sample training period, and then execute trades according to the rule in its succeeding out-of-sample period. We experimentally show that the framework very often results in a profit. We then consider a framework in which we conduct optimization as above and then execute trades in distant out-of-sample periods. We empirically show that the results depend on the similarity of the trends in the training and testing periods.

Original languageEnglish
Title of host publicationProcedia Computer Science
PublisherElsevier
Pages86-98
Number of pages13
Volume13
DOIs
Publication statusPublished - 2012
Event3rd International Neural Network Society Winter Conference, INNS-WC 2012 - Bangkok, Thailand
Duration: 2012 Oct 32012 Oct 5

Other

Other3rd International Neural Network Society Winter Conference, INNS-WC 2012
CountryThailand
CityBangkok
Period12/10/312/10/5

Fingerprint

Profitability
Genetic algorithms
Genetic programming
Testing

Keywords

  • Financial prediction
  • Foreign exchange
  • Genetic algorithm
  • Optimization algorithm
  • Robustness test
  • Technical analysis

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Deng, S., Sun, Y., & Sakurai, A. (2012). Robustness test of genetic algorithm on generating rules for currency trading. In Procedia Computer Science (Vol. 13, pp. 86-98). Elsevier. https://doi.org/10.1016/j.procs.2012.09.117

Robustness test of genetic algorithm on generating rules for currency trading. / Deng, Shangkun; Sun, Yizhou; Sakurai, Akito.

Procedia Computer Science. Vol. 13 Elsevier, 2012. p. 86-98.

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

Deng, S, Sun, Y & Sakurai, A 2012, Robustness test of genetic algorithm on generating rules for currency trading. in Procedia Computer Science. vol. 13, Elsevier, pp. 86-98, 3rd International Neural Network Society Winter Conference, INNS-WC 2012, Bangkok, Thailand, 12/10/3. https://doi.org/10.1016/j.procs.2012.09.117
Deng S, Sun Y, Sakurai A. Robustness test of genetic algorithm on generating rules for currency trading. In Procedia Computer Science. Vol. 13. Elsevier. 2012. p. 86-98 https://doi.org/10.1016/j.procs.2012.09.117
Deng, Shangkun ; Sun, Yizhou ; Sakurai, Akito. / Robustness test of genetic algorithm on generating rules for currency trading. Procedia Computer Science. Vol. 13 Elsevier, 2012. pp. 86-98
@inproceedings{dd9394db78d248f38331ead71f4b318d,
title = "Robustness test of genetic algorithm on generating rules for currency trading",
abstract = "In trading in currency markets, reducing the mean of absolute or squared errors of predicted values is not valuable unless it results in profits. A trading rule is a set of conditions that describe when to buy or sell a currency or to close a position, which can be used for automated trading. To optimize the rule to obtain a profit in the future, a probabilistic method such as a genetic algorithm (GA) or genetic programming (GP) is utilized, since the profit is a discrete and multimodal function with many parameters. Although the rules optimized by GA/GP reportedly obtain a profit in out-of-sample testing periods, it is hard to believe that they yield a profit in distant out-of-sample periods. In this paper, we first consider a framework where we optimize the parameters of the trading rule in an in-sample training period, and then execute trades according to the rule in its succeeding out-of-sample period. We experimentally show that the framework very often results in a profit. We then consider a framework in which we conduct optimization as above and then execute trades in distant out-of-sample periods. We empirically show that the results depend on the similarity of the trends in the training and testing periods.",
keywords = "Financial prediction, Foreign exchange, Genetic algorithm, Optimization algorithm, Robustness test, Technical analysis",
author = "Shangkun Deng and Yizhou Sun and Akito Sakurai",
year = "2012",
doi = "10.1016/j.procs.2012.09.117",
language = "English",
volume = "13",
pages = "86--98",
booktitle = "Procedia Computer Science",
publisher = "Elsevier",

}

TY - GEN

T1 - Robustness test of genetic algorithm on generating rules for currency trading

AU - Deng, Shangkun

AU - Sun, Yizhou

AU - Sakurai, Akito

PY - 2012

Y1 - 2012

N2 - In trading in currency markets, reducing the mean of absolute or squared errors of predicted values is not valuable unless it results in profits. A trading rule is a set of conditions that describe when to buy or sell a currency or to close a position, which can be used for automated trading. To optimize the rule to obtain a profit in the future, a probabilistic method such as a genetic algorithm (GA) or genetic programming (GP) is utilized, since the profit is a discrete and multimodal function with many parameters. Although the rules optimized by GA/GP reportedly obtain a profit in out-of-sample testing periods, it is hard to believe that they yield a profit in distant out-of-sample periods. In this paper, we first consider a framework where we optimize the parameters of the trading rule in an in-sample training period, and then execute trades according to the rule in its succeeding out-of-sample period. We experimentally show that the framework very often results in a profit. We then consider a framework in which we conduct optimization as above and then execute trades in distant out-of-sample periods. We empirically show that the results depend on the similarity of the trends in the training and testing periods.

AB - In trading in currency markets, reducing the mean of absolute or squared errors of predicted values is not valuable unless it results in profits. A trading rule is a set of conditions that describe when to buy or sell a currency or to close a position, which can be used for automated trading. To optimize the rule to obtain a profit in the future, a probabilistic method such as a genetic algorithm (GA) or genetic programming (GP) is utilized, since the profit is a discrete and multimodal function with many parameters. Although the rules optimized by GA/GP reportedly obtain a profit in out-of-sample testing periods, it is hard to believe that they yield a profit in distant out-of-sample periods. In this paper, we first consider a framework where we optimize the parameters of the trading rule in an in-sample training period, and then execute trades according to the rule in its succeeding out-of-sample period. We experimentally show that the framework very often results in a profit. We then consider a framework in which we conduct optimization as above and then execute trades in distant out-of-sample periods. We empirically show that the results depend on the similarity of the trends in the training and testing periods.

KW - Financial prediction

KW - Foreign exchange

KW - Genetic algorithm

KW - Optimization algorithm

KW - Robustness test

KW - Technical analysis

UR - http://www.scopus.com/inward/record.url?scp=84897972526&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897972526&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2012.09.117

DO - 10.1016/j.procs.2012.09.117

M3 - Conference contribution

VL - 13

SP - 86

EP - 98

BT - Procedia Computer Science

PB - Elsevier

ER -