Toward an Understanding of Financial Markets using Multi-agent Games
We report on our use of multi-agent games to understand financial market behavior. In addition to discussing the background to the multi-agent games themselves, we report a technique which may prove useful for forecasting future movements of financial time-series. A third-party game is trained on a black-box time-series, and is then run into the future to extract next-step and multi-step predictions. Such predictions have potential use as the basis for improved risk management and portfolio optimization strategies.
KeywordsTransaction Cost Financial Market Strategy Space Real Market Hedging Strategy
Unable to display preview. Download preview PDF.
- 2.Further details concerning the prediction method were presented elsewhere, see D. Lamper, S. Howison, N.F. Johnson: Phys. Rev. Lett. 88,017902 (2002), and are the subject of a patent applicationGoogle Scholar
- 4.D. Challet, Y.C. Zhang: Physica A 246,407 (1997). See also the Minority Game web-page at http://www.unifr ch/econophysicsGoogle Scholar
- 7.M. Hart, P. Jefferies, N.F. Johnson, P.M. Hui: Physica A 298, 537 (2001); N.F. Johnson, M. Hart, P.M. Hui: Physica A 269, 1 (1999); M. Hart, P. Jefferies, N.F. Johnson, P.M. Hui: Phys. Rev. E 63, 017102 (2000); M. Hart, P. Jefferies, P.M. Hui, N.F. Johnson: Eur. Phys. J. B 20, 547 (2000); N.F. Johnson, P.M. Hui, R. Jonson, T.S. Lo: Phys. Rev. Lett. 82, 3360 (1999)Google Scholar
- 8.P. Ormerod: ‘Surprised by depression’, Financial Times, February 19, 2001Google Scholar
- 9.J.P. Bouchaud, D. Sornette: J. de Phys. 14, 863 (1994). See also J.P. Bouchaud, M. Potters, Theory of Financial Risks ( Cambridge University Press, Cambridge 2000 )Google Scholar