Behavioural GP diversity for dynamic environments: an application in hedge fund investment

ABSTRACT

We present a new mechanism for preserving phenotypic behavioural diversity in a Genetic Programming application for hedge fund portfolio optimization, and provide experimental results on real-world data that indicate the importance of phenotypic behavioural diversity both in achieving higher fitness and in improving the adaptability of the GP population for continuous learning.

REFERENCES

• 1: Markus Brameier , Wolfgang Banzhaf, Explicit Control of Diversity and Effective Variation Distance in Linear Genetic Programming, Proceedings of the 5th European Conference on Genetic Programming, p.37-49, April 03-05, 2002
• 2: Edmund K. Burke , Steven M. Gustafson , Graham Kendall , Natalio Krasnogor, Advanced Population Diversity Measures in Genetic Programming, Proceedings of the 7th International Conference on Parallel Problem Solving from Nature, p.341-350, September 07-11, 2002
• 3: Raymond Burke , Steven Gustafson , Graham Kendall, A Survey And Analysis Of Diversity Measures In Genetic Programming, Proceedings of the Genetic and Evolutionary Computation Conference, p.716-723, July 09-13, 2002
• 4: H. Cobb. An investigation into the use of hypermutation as an adaptive operator in genetic algorithms having continuous, time-dependent nonstationary environments. Technical report, Naval Research Laboratory, 1990.
• 5: Anikó Ekárt , Sandor Z. Németh, Maintaining the Diversity of Genetic Programs, Proceedings of the 5th European Conference on Genetic Programming, p.162-171, April 03-05, 2002
• 6: David E. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1989
• 7: J. Grefenstette. Genetic algorithms for changing environments. In Parallel Problem Solving from Nature 2, pages 137--144. North Holland, 1992.
• 8: C. Karr. Genetic algorithms and fuzzy logic for adaptive process control. In Intelligent Hybrid Systems, S.Goonatilake and S.Khebbal, eds. Wiley, 1995.
• 9: R. Keller and W. Banzhaf. Explicit maintenance of genetic diversity on genospaces. In Unpublished Manuscript, 1994.
• 10: M. Kidwell and D. Cook. Genetic algorithm for dynamic task scheduling. In In Proceeding of the IEEE 13th International Phoenix Conference on Computers and Communications, pages 61--67, 1994.
• 11: Shane Legg , Marcus Hutter, Fitness uniform deletion: a simple way to preserve diversity, Proceedings of the 2005 conference on Genetic and evolutionary computation, June 25-29, 2005, Washington DC, USA [doi>10.1145/1068009.1068216]
• 12: B. Malkiel. A Random Walk Down Wall Street. W.W. Norton & Company, ISBN: 0393057828, 2003.
• 13: R. McKay. Fitness sharing in genetic programming. In Proceedings of the Genetic and Evolutionary Computation Conference, pages 435--442, 2000.
• 14: R. Mckay and H. Abbass. Anticorrelation measures in genetic programming. In Australian-Japan Workshop on Intelligent and Evolutionary System, pages 45--51, 2001.
• 15: P. Monsieur and E. Flerackers. Increasing the diversity of a population in genetic programming. In Proceeding of Genetic and Evolutionary Computation Conference (GECCO), page 185. Morgan Kaufmann, 2001.
• 16: C. Reeves and H. Karata. Dynamic sequencing of a multi-processor system: a genetic algorithm approach. In Artificial Neural Nets and Genetic Algorithms. Springer, 1993.
• 17: J. Rosca. Entropy-driven adaptive representation. In Proc. Workshop Genetic Programming: From Theory to Real-World Applications, J. Rosca, Ed., pages 23--32, 1995.
• 18: J. Rosca. Genetic programming exploratory power and the discovery of function. In Proc. Nat'l. Conf. on Evolutionary Programming, 1995.
• 19: C. Schoreels and J. M. Garibaldi. The effect of varying parameter on performance for adaptive agents in techical equity market trading. In Proceedings of the 3rd IEEE Internatioal Conference on Computational Cybernetics (ICCC 2005), 2005.
• 20: W. Sharpe. Risk, market sensitivity, and diversification. Financial Analysts Journal (January/February 1972), pages 74--79, 1972.
• 21: W. F. Sharpe. The sharpe ratio. J. Portfolio Management, 21:49--58, 1994.
• 22: Rasmus K. Ursem, Diversity-Guided Evolutionary Algorithms, Proceedings of the 7th International Conference on Parallel Problem Solving from Nature, p.462-474, September 07-11, 2002

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.m Miscellaneous

General Terms:
Algorithms, Experimentation

Keywords:
adaptation, diversity, dynamic environment, finance, genetic programming, phenotype