Advertisement

An Application a Two-Level Determination Consensus Method in a Multi-agent Financial Decisions Support System

  • Adrianna Kozierkiewicz
  • Marcin HernesEmail author
  • Thanh Tung Nguyen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11431)

Abstract

Supporting financial decisions, including Foreign Exchange Market (Forex) is recently realized more often by using multi-agent systems. On this market currencies are traded against one another in pairs. The quotations are in High Frequency Trading. The supporting decisions on Forex rely on provide, by a multi-agent system, as soon as possible advice on what position should be taken: long, short or none. This advice is given by different investment strategies based on agents running based on statistics, economics, mathematics or artificial intelligence methods. However, these strategies are not optimized in terms of HFT (the computational complexity of these strategies is too high and the signals for open/close positions are too late in many cases). Due this fact, the main problem which appear concerns decreasing a computational complexity of the strategy applied in a multi-agent financial decisions support system. In our research we have assumed that for building HFT investment strategy in a-Trader system, the consensus methods are applied. In many cases determination a consensus is impossible to achieve in the required time using only a one-level determination method in which all of the incoming agents’ knowledge is processed at the same time. A decomposition of a task of determining a consensus into smaller subtasks and their parallelization can solve the mentioned problem. The aim of this paper is to develop a method for a multi-level consensus determining, in order to build a HFT investment strategy in a-Trader multi-agent system.

Keywords

Consensus Multi-agent system Forex 

Notes

Acknowledgement

This research was performed in the frame of the project “Business Data Mining A-Trader” realized in cooperation with 4-TUNE IT s.c. (http://4tune.pl) and project no. 4005/0011/17, “Smart University”, Nguyen Tat Thanh University, Vietnam.

References

  1. 1.
    Korczak, J., Hernes, M., Bac, M.: Collective intelligence supporting trading decisions on FOREX market. In: Nguyen, N.T., Papadopoulos, George A., Jędrzejowicz, P., Trawiński, B., Vossen, G. (eds.) ICCCI 2017. LNCS (LNAI), vol. 10448, pp. 113–122. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-67074-4_12CrossRefGoogle Scholar
  2. 2.
    Barbosa, R.P., Belo, O.: Multi-agent forex trading system. In: Hãkansson, A., Hartung, R., Nguyen, N.T. (eds.) Agent and Multi-agent Technology for Internet and Enterprise Systems. SCI, vol. 289, pp. 91–118. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-13526-2_5CrossRefGoogle Scholar
  3. 3.
    Sycara, K.P., Decker, K., Zeng, D.: Intelligent agents in portfolio management. In: Jennings, N., Wooldridge, M. (eds.) Agent Technology, pp. 267–282. Springer, Heidelberg (2002).  https://doi.org/10.1007/978-3-662-03678-5_14CrossRefGoogle Scholar
  4. 4.
    Tatikunta, R., Rahimi, S., Shrestha, P., Bjursel, J.: TrAgent: a multi-agent system for stock exchange. In: Proceedings of the 2006 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IATW 2006), pp. 505–509. IEEE Computer Society, Washington, DC, USA (2006)Google Scholar
  5. 5.
    Ivanović, M., Vidaković, M., Budimac, Z., Mitrović, D.: A scalable distributed architecture for client and server-side software agents. Vietnam J. Comput. Sci. 4(2), 127–137 (2017)CrossRefGoogle Scholar
  6. 6.
    Sher, G.I.: Forex trading using geometry sensitive neural networks. In: Soule, T. (ed.) Proceedings of the 14th Annual Conference Companion on Genetic and Evolutionary Computation (GECCO 2012), pp. 1533–1534. ACM, New York (2012)Google Scholar
  7. 7.
    Khosravi, H., Shiri, Mohammad E., Khosravi, H., Iranmanesh, E., Davoodi, A.: TACtic- a multi behavioral agent for trading agent competition. In: Sarbazi-Azad, H., Parhami, B., Miremadi, S.-G., Hessabi, S. (eds.) CSICC 2008. CCIS, vol. 6, pp. 811–815. Springer, Heidelberg (2008).  https://doi.org/10.1007/978-3-540-89985-3_109CrossRefGoogle Scholar
  8. 8.
    Bohm, V., Wenzelburger, J.: On the performance of efficient portfolios. J. Econ. Dyn. Control 29(4), 721–740 (2005)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Korczak, J, Hernes, M., Bac M.: Risk avoiding strategy in multi-agent trading system. In: Proceedings of Federated Conference Computer Science and Information Systems (FedCSIS), Kraków, pp. 1131–1138 (2013)Google Scholar
  10. 10.
    Hernes, M., Sobieska-Karpińska, J.: Application of the consensus method in a multiagent financial decision support system. IseB 14(1), 167–185 (2016)CrossRefGoogle Scholar
  11. 11.
    Kozierkiewicz-Hetmańska A., Nguyen N.T.: A comparison analysis of consensus determining using one and two-level methods. In: Advances in Knowledge-Based and Intelligent Information and Engineering Systems, vol. 243, pp. 159–168 (2012)Google Scholar
  12. 12.
    Nguyen, V.D., Nguyen, N.T.: A two-stage consensus-based approach for determining collective knowledge. In: Le Thi, H., Nguyen, N., Do, T. (eds.) Advanced Computational Methods for Knowledge Engineering, pp. 301–310. Springer, Heidelberg (2015).  https://doi.org/10.1007/978-3-319-17996-4_27CrossRefGoogle Scholar
  13. 13.
    Kozierkiewicz-Hetmańska, A., Sitarczyk, M.: The efficiency analysis of the multi-level consensus determination method. In: Nguyen, N.T., Papadopoulos, George A., Jędrzejowicz, P., Trawiński, B., Vossen, G. (eds.) ICCCI 2017. LNCS (LNAI), vol. 10448, pp. 103–112. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-67074-4_11CrossRefGoogle Scholar
  14. 14.
    Kozierkiewicz-Hetmanska, A., Pietranik, M.: The knowledge increase estimation framework for ontology integration on the concept level. J. Intell. Fuzzy Syst. 32(2), 1–12 (2016)zbMATHGoogle Scholar
  15. 15.
    Hernes, M., Sobieska-Karpińska, J., Kozierkiewicz, A., Pietranik, M.: A new distance function for consensus determination in decision support systems. In: Nguyen, N.T., Pimenidis, E., Khan, Z., Trawiński, B. (eds.) ICCCI 2018. LNCS (LNAI), vol. 11056, pp. 155–165. Springer, Cham (2018).  https://doi.org/10.1007/978-3-319-98446-9_15CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Faculty of Computer Science and ManagementWroclaw University of Science and TechnologyWrocławPoland
  2. 2.Wrocław University of EconomicsWrocławPoland
  3. 3.Nguyen Tat Thanh UniversityHo Chi Minh CityVietnam

Personalised recommendations