Skip to main content
Log in

Automated asset management based on partially cooperative agents for a world of risks

Applied Intelligence Aims and scope Submit manuscript

Abstract

Despite the fact any investor prefers lower risk and higher return, investors may have different preferences about what would be an acceptable risk or a minimal return. For instance, some investors prefer to have a lower bound risk rather than gaining a higher return. In portfolio theory, it is commonly assumed the existence of one risk free asset that offers a positive return. This theoretical risk free asset combined with a risky portfolio creates a new portfolio that presents a linear relation between risk and return as the risk free asset weight (w f ) changes. Hence, any level of risk or of return is easy to achieve separately, just by changing w f . However, in a world without any risk free assets, the combination between assets creates nonlinear portfolios. Achieving a specific level of risk or return is not a trivial task. In this paper, we assume a risky world rather than the existence of a risk free asset, in order to model an automated asset management system. Furthermore, some automated asset managers give very different results when evolving in different contexts: hence, a very profitable manager can have very bad results in other market situations. This paper presents a multiagent architecture, aiming to tackle these problems. The architecture, named COAST (COmpetitive Agent SocieTy), is based on competitive agents that act autonomously on behalf of an investor in financial asset management. It allows the simultaneous and competitive use of several asset analysis techniques currently applied in the finance field. Some dedicated agents, called advisors, apply a particular technique to a single asset. The results provided by these advisors are then submitted to and analyzed by a special agent called coach, who evaluates its advisors’ performance and defines an expectation about the future price of one specific asset. Within COAST, several coaches negotiate to define the best money allocation among different assets, by using a negotiation protocol defined in this paper. We also propose an investor description model that is able to represent different investors’ preferences with defined acceptable limits of risk and/or return. The COAST architecture was designed to operate adequately with any possible investor’s preference. It was implemented using a financial market simulator called AgEx and tested using real data from the Nasdaq stock exchange. The test results show that the architecture performed well when compared to an adjusted market index.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

Notes

  1. There is only one single best coach per negotiation cycle; in the case of tie, one of them is randomly selected.

References

  1. Aldridge I (2009) High-frequency trading: a practical guide to algorithmic strategies and trading systems. Wiley, New York

    Google Scholar 

  2. Araujo CHD, Castro PAL (2010) Towards automated trading based on fundamentalist and technical data. In: Proceedings of 20th SBIA, São Bernado do Campo, Brazil. LNAI. Springer, Berlin, pp 704–715

    Google Scholar 

  3. Cañete A, Constanzo J, Salinas L (2008) Kernel price pattern trading. Appl Intell 29:152–156. doi:10.1007/s10489-007-0054-2

    Article  Google Scholar 

  4. Castro PA, Sichman JS (2007) Towards cooperation among competitive trader agents. In: Proceedings of 9th ICEIS, Funchal, Portugal, pp 138–143

    Google Scholar 

  5. Castro PA, Sichman JS (2009) Agex: a financial market simulation tool for software agents. In: Aalst W, Mylopoulos J, Sadeh NM, Shaw MJ, Szyperski C, Filipe J, Cordeiro J (eds) LNBIP, vol 24. Springer, Berlin, pp 704–715

    Google Scholar 

  6. Decker K, Pannu A, Sycara K, Williamson M (1997) Designing behaviors for information agents. In: Johnson WL, Hayes-Roth B (eds) Proceedings of the first international conference on autonomous agents (Agents’97). ACM, New York, pp 404–412

    Chapter  Google Scholar 

  7. Dougherty ER (1990) Probability and statistics for the engineering, computing, and physical sciences. Prentice Hall, Englewood Cliffs

    MATH  Google Scholar 

  8. Durbin M (2010) All about high-frequency trading. McGraw-Hill, New York

    Google Scholar 

  9. Fabio Bellifemine GC, Greenwood D (2007) Developing multi-agent systems with JADE. Wiley, Chichester

    Book  Google Scholar 

  10. Farmer JD, Foley D (2009) The economy needs agent-based modelling. Nature 460:685–686

    Article  Google Scholar 

  11. Feng X, Jo C-H (2003) Agent-based stock trading. In: Proceedings of the ISCA CATA-2003, Honolulu, USA

    Google Scholar 

  12. Francis JC (1983) Management of investments. McGraw-Hill, New York

    Google Scholar 

  13. Garcia MEF, Marin EA, Garcia RQ (2010) Improving return using risk-return adjustment and incremental training in technical trading rules with gaps. Appl Intell 33(2):93–106

    Article  Google Scholar 

  14. Kearns M, Ortiz L (2003) The Penn-Lehman automated trading project. IEEE Intell Syst 18(6):22–31

    Article  Google Scholar 

  15. Kendall G, Su Y (2003) Co-evolution of successful trading strategies in a simulated stock market. In: Proceedings of the 2003 international conference on machine learning and applications (ICMLA’03), Los Angeles, pp 200–206

    Google Scholar 

  16. Kendall G, Su Y (2005) A particle swarm optimisation approach in the construction of optimal risky portfolios. In: Proceedings of the 23rd IASTED international multi-conference artificial intelligence and applications, Innsbruck, Austria, pp 140–145

    Google Scholar 

  17. Lee S, Ahn J, Oh K, Kim T (2010) Using rough set to support investment strategies of real-time trading in futures market. Appl Intell 32:364–377. doi:10.1007/s10489-008-0150-y

    Article  Google Scholar 

  18. Markowitz HM (1952) Portfolio selection. J Finance 7(1):77–91

    Google Scholar 

  19. Mochón A, Quintana D, Sáez Y, Isasi P (2008) Soft computing techniques applied to finance. Appl Intell 29:111–115. doi:10.1007/s10489-007-0051-5

    Article  Google Scholar 

  20. Pedrycz W, Gomide F (1998) An introduction to fuzzy sets: analysis and design. MIT Press, Cambridge

    MATH  Google Scholar 

  21. Rosenschein JS, Zlotkin G (1994) Rules of encounter: designing conventions for automated negotiation among computers. MIT Press, Boston

    Google Scholar 

  22. Russell S, Norvig P (2003) Artificial intelligence. A modern approach, 2nd edn. Prentice Hall, Englewood Cliffs

    Google Scholar 

  23. Sharpe WF (1994) The Sharpe ratio. J Portf Manag 13(3):227–286

    MathSciNet  Google Scholar 

  24. Sherstov A, Stone P (2004) Three automated stock-trading agents: a comparative study. In: Proceedings of the agent mediated electronic commerce (AMEC) workshop—AAMAS 2004, New York

    Google Scholar 

  25. Shoham Y, Leyton-Brown K (2009) Multiagent systems: algorithmic, game-theoretic, and logical foundations. Cambridge University Press, New York

    MATH  Google Scholar 

  26. Smith RG (1980) The contract net protocol: high-level communication and control in a distributed problem solver. IEEE Trans Comput 29(12):1104–1113

    Article  Google Scholar 

  27. Sortino F A, Forsey HJ (1996) On the use and misuse of downside risk. J Portf Manag 22(1):35–42

    Article  Google Scholar 

  28. Tan A, Quek C, Yow K (2008) Maximizing winning trades using a novel rspop fuzzy neural network intelligent stock trading system. Appl Intell 29:116–128. doi:10.1007/s10489-007-0055-1

    Article  Google Scholar 

  29. Weiss G (1999) Multiagent systems: a modern approach to distributed artificial intelligence. MIT Press, Cambridge

    Google Scholar 

  30. Wooldridge M (2002) An introduction to multiagent systems. Wiley, London

    Google Scholar 

  31. Yuan Luo KL, Davis DN (2002) A multi-agent decision support system for stock trading. IEEE Netw 16(1):20–27

    Article  Google Scholar 

Download references

Acknowledgements

Jaime Sichman is partially funded by CNPq and FAPESP, Brazil. Paulo Castro thanks Prof. Alexander Brodsky from George Mason University for the basic idea of the N34 agent.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Paulo André Lima de Castro.

Rights and permissions

Reprints and permissions

About this article

Cite this article

de Castro, P.A.L., Sichman, J.S. Automated asset management based on partially cooperative agents for a world of risks. Appl Intell 38, 210–225 (2013). https://doi.org/10.1007/s10489-012-0366-8

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-012-0366-8

Keywords

Navigation