Developing actionable trading agents

Longbing Cao and Xuezhong (Tony) He ()
Additional contact information
Longbing Cao: Faculty of Engineering and Information Technology, University of Technology Sydney

Published Paper Series from Finance Discipline Group, UTS Business School, University of Technology, Sydney

Abstract: Trading agents are useful for developing and back-testing quality trading strategies to support smart trading actions in the market. However, most of the existing trading agent research oversimplifies trading strategies, and focuses on simulated ones. As a result, there exists a big gap between the deliverables and business needs when the developed strategies are deployed into the real life. Therefore, the actionable capability of developed trading agents is often very limited. This paper for the first time introduces effective approaches for optimizing and integrating multiple classes of strategies through trading agent collaboration. An integration and optimization approach is proposed to identify optimal trading strategy in each category, and further integrate optimal strategies crossing classes. Positions associated with these optimal strategies are recommended for trading agents to take actions in the market. Extensive experiments on a large quantity of real-life market data show that trading agents following the recommended strategies have great potential to obtain high benefits while low costs. This verifies that it is promising to develop trading agents toward workable and satisfying business needs.

Keywords: Trading agent; Trading strategy; Optimization; Integration (search for similar items in EconPapers)
Pages: 16 pages
Date: 2009-01-01
References: Add references at CitEc
Citations: View citations in EconPapers (2)

Published in: Cao, L. and He, X., 2009, "Developing actionable trading agents", Knowledge And Information Systems, 18(2), 183-192.

Downloads: (external link)
https://link.springer.com/content/pdf/10.1007%2Fs10115-008-0170-2.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:uts:ppaper:2009-5

Access Statistics for this paper

More papers in Published Paper Series from Finance Discipline Group, UTS Business School, University of Technology, Sydney PO Box 123, Broadway, NSW 2007, Australia. Contact information at EDIRC.
Bibliographic data for series maintained by Duncan Ford ().