Title: Agent-based evolutionary optimisation of trading strategies

Authors: Jiarui Ni, Dan Luo, Yuming Ou, Chao Luo

Addresses: University of Technology, Sydney, GPO Box 123, Broadway, NSW 2007, Australia. ' University of Technology, Sydney, GPO Box 123, Broadway, NSW 2007, Australia. ' University of Technology, Sydney, GPO Box 123, Broadway, NSW 2007, Australia. ' University of Technology, Sydney, GPO Box 123, Broadway, NSW 2007, Australia

Abstract: The backtesting and optimisation of trading strategies has emerged as an interesting research and experimental problem in both finance and Information Technology (IT) fields. However, it is a non-trivial task to effectively and efficiently optimise trading strategies, not to mention the optimisation in the real-world situations. This paper discusses the application of evolutionary technologies (genetic algorithm in particular) to the optimisation of trading strategies. Experimental results show that this approach is promising. Due to the complexity involved in the optimisation process, we further present an agent-based system that can help users easily specify and execute optimisation jobs to their advantages.

Keywords: genetic algorithms; GAs; optimisation; agents; multi-agent systems; MAS; agent-based systems; trading strategies; data mining; stock data.

DOI: 10.1504/IJIIDS.2008.017243

International Journal of Intelligent Information and Database Systems, 2008 Vol.2 No.1, pp.25 - 48

Published online: 20 Feb 2008 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article