Acquiring a Government Bond Trading Strategy Using Reinforcement Learning

Tohgoroh Matsui; Takashi Goto; Kiyoshi Izumi

doi:10.20965/jaciii.2009.p0691

single-jc.php

« previous

JACIII Vol.13 No.6 pp. 691-696

doi: 10.20965/jaciii.2009.p0691

(2009)

Paper:

Views over last 60 days: 1,045

Acquiring a Government Bond Trading Strategy Using Reinforcement Learning

Tohgoroh Matsui^, Takashi Goto^, and Kiyoshi Izumi^

^*Tohgoroh Machine Learning Research Institute, Chiba, Japan

^**The Bank of Tokyo-Mitsubishi UFJ, Ltd., Tokyo, Japan

^***National Institute of Advanced Industrial Science and Technology, Tokyo, Japan

Received:

April 20, 2009

Accepted:

July 31, 2009

Published:

November 20, 2009

Keywords:

machine learning, reinforcement learning, finance, trading strategy

Abstract

This paper proposes using reinforcement learning to acquire a government bond trading strategy. We applied this method to the 10-year Japanese government bond (JGB) market and confirmed that it acquires profitable trading even in extrapolation.

Cite this article as:

T. Matsui, T. Goto, and K. Izumi, “Acquiring a Government Bond Trading Strategy Using Reinforcement Learning,” J. Adv. Comput. Intell. Intell. Inform., Vol.13 No.6, pp. 691-696, 2009.

Data files:

References

[1] P. Kaufman, “Smarter trading: Improving performance in changing markets,” McGraw-Hill Professional, 1995.
[2] A. Sherstov and P. Stone, “Three automated stock-trading agents: A comparative study,” In Proc. of the AAMAS 2004 Workshop on Agent-Mediated Electronic Commerce (AMEC 2004), pp. 173-187, 2004.
[3] F. Bertoluzzo and M. Corazza, “Making financial trading by recurrent reinforcement learning,” In Proc. of the 11th Int. Conf. on Knowledge-Based Intelligent Information and Engineering Systems (KES 2007), Part 2, pp. 619-626, 2007.
[4] J. W. Lee, J. Park, J. O, J. Lee, and E. Hong, “A multiagent approach to Q-learning for daily stock trading,” IEEE Trans. on System, Man and Cybernetics, Part A, Vol.37, No.6, pp. 864-877, 2007.
[5] G. Bates, M. Dempster, and Y. Romahi, “Evolutionary reinforcement learning in FX order book and order flow analysis,” In Proc. of the 2003 IEEE Int. Conf. on Computational Intelligence for Financial Engineering (CIFEr 2003), pp. 355-362, 2003.
[6] C. Gold, “FX trading via recurrent reinforcement learning,” In Proc. of the 2003 IEEE Int. Workshop on Computational Intelligence for Financial Engineering (CIFEr 2003), pp. 363-370, 2003.
[7] J. Bollinger, “Bollinger on Bollinger bands,” McGraw-Hill Professional, 2001.
[8] T. Matsui, N. Inuzuka, and H. Seki, “On-line profit sharing works efficiently,” In Proc. of the 7th Int. Conf. on Knowledge-Based Intelligent Information and Engineering Systems (KES 2003), Part 1, pp. 317-324, 2003.
[9] R. S. Sutton and A. G. Barto, “Reinforcement learning: An introduction,” The MIT Press, 1998.
[10] C. Watkins and P. Dayan, “Q-learning,” Machine Learning, Vol.8, No.3/4, pp. 279-292, 1992.
[11] G. Rummery and M. Niranjan, “On-line Q-learning using connectionist systems,” Report CUED/F-INFENG-RT 116, Engineering Department, Cambridge University, 1994.

This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

[1] [1] P. Kaufman, “Smarter trading: Improving performance in changing markets,” McGraw-Hill Professional, 1995.

[2] [2] A. Sherstov and P. Stone, “Three automated stock-trading agents: A comparative study,” In Proc. of the AAMAS 2004 Workshop on Agent-Mediated Electronic Commerce (AMEC 2004), pp. 173-187, 2004.

[3] [3] F. Bertoluzzo and M. Corazza, “Making financial trading by recurrent reinforcement learning,” In Proc. of the 11th Int. Conf. on Knowledge-Based Intelligent Information and Engineering Systems (KES 2007), Part 2, pp. 619-626, 2007.

[4] [4] J. W. Lee, J. Park, J. O, J. Lee, and E. Hong, “A multiagent approach to Q-learning for daily stock trading,” IEEE Trans. on System, Man and Cybernetics, Part A, Vol.37, No.6, pp. 864-877, 2007.

[5] [5] G. Bates, M. Dempster, and Y. Romahi, “Evolutionary reinforcement learning in FX order book and order flow analysis,” In Proc. of the 2003 IEEE Int. Conf. on Computational Intelligence for Financial Engineering (CIFEr 2003), pp. 355-362, 2003.

[6] [6] C. Gold, “FX trading via recurrent reinforcement learning,” In Proc. of the 2003 IEEE Int. Workshop on Computational Intelligence for Financial Engineering (CIFEr 2003), pp. 363-370, 2003.

[7] [7] J. Bollinger, “Bollinger on Bollinger bands,” McGraw-Hill Professional, 2001.

[8] [8] T. Matsui, N. Inuzuka, and H. Seki, “On-line profit sharing works efficiently,” In Proc. of the 7th Int. Conf. on Knowledge-Based Intelligent Information and Engineering Systems (KES 2003), Part 1, pp. 317-324, 2003.

[9] [9] R. S. Sutton and A. G. Barto, “Reinforcement learning: An introduction,” The MIT Press, 1998.

[10] [10] C. Watkins and P. Dayan, “Q-learning,” Machine Learning, Vol.8, No.3/4, pp. 279-292, 1992.

[11] [11] G. Rummery and M. Niranjan, “On-line Q-learning using connectionist systems,” Report CUED/F-INFENG-RT 116, Engineering Department, Cambridge University, 1994.

Acquiring a Government Bond Trading Strategy Using Reinforcement Learning

Tohgoroh Matsui*, Takashi Goto**, and Kiyoshi Izumi***

Tohgoroh Matsui^, Takashi Goto^, and Kiyoshi Izumi^