Title
A trading method in FX using evolutionary algorithms: extensions based on reverse trend and settlement timing
Abstract
In foreign exchange (FX) markets, the key issues to achieve profitable trading rules are the combination of the indicators, selection of their parameters, and decision of the trade timing for orders and settlements. In this paper, we present a trading system using a combination of genetic algorithm (GA) and genetic programming (GP). Unlike related researches on this problem, our work focuses on two aspects. First, a calculation of appropriate settlement timing is proposed, to make more profits and less losses. Second, reverse trend data are generated using in-sample data, to overcome the overfitting problem and suppress the risk of loss. To examine the effectiveness of the method, we employed simulations using real-world trading intraday data. It is verified the enhanced capability of our method to make consistent gain out-of-sample and avoid large draw-downs.
Year
DOI
Venue
2011
10.1145/2001858.2001937
GECCO (Companion)
Keywords
Field
DocType
real-world trading intraday data,appropriate settlement timing,genetic algorithm,reverse trend data,genetic programming,evolutionary algorithm,trade timing,trading system,trading method,in-sample data,overfitting problem,profitable trading rule,technical analysis,profitability,optimization,finance
Risk of loss,Trading strategy,Mathematical optimization,Evolutionary algorithm,Computer science,Genetic programming,Overfitting,Genetic algorithm,Profit (economics),Technical analysis
Conference
Citations 
PageRank 
References 
1
0.46
3
Authors
3
Name
Order
Citations
PageRank
Badarch Tserenchimed110.46
Shu Liu210.46
Hitoshi Iba31541138.51