Foreign exchange trading rules using a single technical indicator from multiple timeframes

Shangkun Deng, Akito Sakurai

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

7 Citations (Scopus)

Abstract

This study applies a genetic algorithm (GA) to generate trading rules for currency trading based on a single technical indicator named the Relative Strength Index (RSI) as well as multiple timeframes from which we extract the feature. The target trading currency pair is EUR/USD and trading time horizon is one hour. Using more than one timeframe may improve the assessment of the overbought or oversold conditions of the target currency pair, since different traders may have different trading time horizons and thus a trader may consider the overall condition for trading a currency pair from both its longer and shorter timeframes. Therefore, this paper uses a combined signal from a relatively longer timeframe (two hours) and a relatively shorter timeframe (30 minutes), other than the target timeframe (one hour). In addition, since the parameters of the RSI are also crucial for obtaining the best trading rules, we use a GA to search for the best parameters of each RSI. Moreover, we design a GA chromosome to encode trading timing by designating when to buy, sell, and close the position. The experimental results presented in this paper show that the combined signal from multiple timeframes, including that from the target timeframe, improves trading performance.

Original languageEnglish
Title of host publicationProceedings - 27th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2013
Pages207-212
Number of pages6
DOIs
Publication statusPublished - 2013
Event27th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2013 - Barcelona, Spain
Duration: 2013 Mar 252013 Mar 28

Other

Other27th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2013
CountrySpain
CityBarcelona
Period13/3/2513/3/28

Fingerprint

Genetic algorithms
Chromosomes

Keywords

  • Currency Trading
  • Genetic Algorithm
  • Multiple Time Frames
  • Technical Indicator
  • Trading Rule

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications

Cite this

Deng, S., & Sakurai, A. (2013). Foreign exchange trading rules using a single technical indicator from multiple timeframes. In Proceedings - 27th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2013 (pp. 207-212). [6550398] https://doi.org/10.1109/WAINA.2013.7

Foreign exchange trading rules using a single technical indicator from multiple timeframes. / Deng, Shangkun; Sakurai, Akito.

Proceedings - 27th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2013. 2013. p. 207-212 6550398.

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

Deng, S & Sakurai, A 2013, Foreign exchange trading rules using a single technical indicator from multiple timeframes. in Proceedings - 27th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2013., 6550398, pp. 207-212, 27th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2013, Barcelona, Spain, 13/3/25. https://doi.org/10.1109/WAINA.2013.7
Deng S, Sakurai A. Foreign exchange trading rules using a single technical indicator from multiple timeframes. In Proceedings - 27th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2013. 2013. p. 207-212. 6550398 https://doi.org/10.1109/WAINA.2013.7
Deng, Shangkun ; Sakurai, Akito. / Foreign exchange trading rules using a single technical indicator from multiple timeframes. Proceedings - 27th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2013. 2013. pp. 207-212
@inproceedings{44e32daf6f474fec8b3402d66fc3db37,
title = "Foreign exchange trading rules using a single technical indicator from multiple timeframes",
abstract = "This study applies a genetic algorithm (GA) to generate trading rules for currency trading based on a single technical indicator named the Relative Strength Index (RSI) as well as multiple timeframes from which we extract the feature. The target trading currency pair is EUR/USD and trading time horizon is one hour. Using more than one timeframe may improve the assessment of the overbought or oversold conditions of the target currency pair, since different traders may have different trading time horizons and thus a trader may consider the overall condition for trading a currency pair from both its longer and shorter timeframes. Therefore, this paper uses a combined signal from a relatively longer timeframe (two hours) and a relatively shorter timeframe (30 minutes), other than the target timeframe (one hour). In addition, since the parameters of the RSI are also crucial for obtaining the best trading rules, we use a GA to search for the best parameters of each RSI. Moreover, we design a GA chromosome to encode trading timing by designating when to buy, sell, and close the position. The experimental results presented in this paper show that the combined signal from multiple timeframes, including that from the target timeframe, improves trading performance.",
keywords = "Currency Trading, Genetic Algorithm, Multiple Time Frames, Technical Indicator, Trading Rule",
author = "Shangkun Deng and Akito Sakurai",
year = "2013",
doi = "10.1109/WAINA.2013.7",
language = "English",
isbn = "9780769549521",
pages = "207--212",
booktitle = "Proceedings - 27th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2013",

}

TY - GEN

T1 - Foreign exchange trading rules using a single technical indicator from multiple timeframes

AU - Deng, Shangkun

AU - Sakurai, Akito

PY - 2013

Y1 - 2013

N2 - This study applies a genetic algorithm (GA) to generate trading rules for currency trading based on a single technical indicator named the Relative Strength Index (RSI) as well as multiple timeframes from which we extract the feature. The target trading currency pair is EUR/USD and trading time horizon is one hour. Using more than one timeframe may improve the assessment of the overbought or oversold conditions of the target currency pair, since different traders may have different trading time horizons and thus a trader may consider the overall condition for trading a currency pair from both its longer and shorter timeframes. Therefore, this paper uses a combined signal from a relatively longer timeframe (two hours) and a relatively shorter timeframe (30 minutes), other than the target timeframe (one hour). In addition, since the parameters of the RSI are also crucial for obtaining the best trading rules, we use a GA to search for the best parameters of each RSI. Moreover, we design a GA chromosome to encode trading timing by designating when to buy, sell, and close the position. The experimental results presented in this paper show that the combined signal from multiple timeframes, including that from the target timeframe, improves trading performance.

AB - This study applies a genetic algorithm (GA) to generate trading rules for currency trading based on a single technical indicator named the Relative Strength Index (RSI) as well as multiple timeframes from which we extract the feature. The target trading currency pair is EUR/USD and trading time horizon is one hour. Using more than one timeframe may improve the assessment of the overbought or oversold conditions of the target currency pair, since different traders may have different trading time horizons and thus a trader may consider the overall condition for trading a currency pair from both its longer and shorter timeframes. Therefore, this paper uses a combined signal from a relatively longer timeframe (two hours) and a relatively shorter timeframe (30 minutes), other than the target timeframe (one hour). In addition, since the parameters of the RSI are also crucial for obtaining the best trading rules, we use a GA to search for the best parameters of each RSI. Moreover, we design a GA chromosome to encode trading timing by designating when to buy, sell, and close the position. The experimental results presented in this paper show that the combined signal from multiple timeframes, including that from the target timeframe, improves trading performance.

KW - Currency Trading

KW - Genetic Algorithm

KW - Multiple Time Frames

KW - Technical Indicator

KW - Trading Rule

UR - http://www.scopus.com/inward/record.url?scp=84881417982&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881417982&partnerID=8YFLogxK

U2 - 10.1109/WAINA.2013.7

DO - 10.1109/WAINA.2013.7

M3 - Conference contribution

AN - SCOPUS:84881417982

SN - 9780769549521

SP - 207

EP - 212

BT - Proceedings - 27th International Conference on Advanced Information Networking and Applications Workshops, WAINA 2013

ER -