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 language | English |
|---|---|
| Title of host publication | Procedia Computer Science |
| Publisher | Elsevier |
| Pages | 86-98 |
| Number of pages | 13 |
| Volume | 13 |
| DOIs | |
| Publication status | Published - 2012 |
| Event | 3rd International Neural Network Society Winter Conference, INNS-WC 2012 - Bangkok, Thailand Duration: 2012 Oct 3 → 2012 Oct 5 |
Other
| Other | 3rd International Neural Network Society Winter Conference, INNS-WC 2012 |
|---|---|
| Country | Thailand |
| City | Bangkok |
| Period | 12/10/3 → 12/10/5 |
Fingerprint
Keywords
- Financial prediction
- Foreign exchange
- Genetic algorithm
- Optimization algorithm
- Robustness test
- Technical analysis
ASJC Scopus subject areas
- Computer Science(all)
Cite this
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 proceeding › Conference contribution
}
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 -