Diverse committees vote for dependable profits

ABSTRACT

Stock selection for hedge fund portfolios is a challenging problem for Genetic Programming (GP) because the markets (the environment in which the GP solution must survive) are dynamic, unpredictable and unforgiving. How can GP be improved so that solutions are produced that are robust to non-trivial changes in the environment? We explore an approach that uses a voting committee of GP individualswith differing phenotypic behaviour.

REFERENCES

• 1: V. S. Aragon and S. C. Esquivel. An evolutionary algorithm to track changes of optimum value locations in dynamic environments. Journal of Computer Science and Technology, 4(3):127--134, 2004.
• 2: T. F. Bersano-Begey and J. M. Daida. A discussion on generality and robustness and a framework for fitness set construction in genetic programming to promote robustness. In JR. Koza, editor, Late Breaking Papers at the 1997 Genetic Programming Conference, pages 11--18, Stanford University, CA, USA, 13--16 July 1997. Stanford Bookstore.
• 3: C. P. Bowers. Formation of modules in a computational model of embryogeny. In The 2005 IEEE Congress on Evolutionary Computation, volume~1, pages 537--542, 2005.
• 4: Jürgen Branke, Creating Robust Solutions by Means of Evolutionary Algorithms, Proceedings of the 5th International Conference on Parallel Problem Solving from Nature, p.119-128, September 27-30, 1998
• 5: G. Brown, J. Wyatt, R. Harris, and X. Yao. Diversity creation methods: a survey and categorisation. Information Fusion, 6(1):5--20, 2005.
• 6: B. Buxton, W. B. Langdon, and S. J. Barrett. Data fusion by intelligent classifier combination. Measurement and Control}, 34(8):229--234, 2001.
• 7: Thomas G. Dietterich, Ensemble Methods in Machine Learning, Proceedings of the First International Workshop on Multiple Classifier Systems, p.1-15, June 21-23, 2000
• 8: J. P. Egan. Signal Detection Theory and ROC Analysis. Academic Press, 1975.
• 9: J. Michael Fitzpatrick , John J. Grefenstette, Genetic Algorithms in Noisy Environments, Machine Learning, v.3 n.2-3, p.101-120, October 1988 [doi>10.1007/BF00113893]
• 10: A. Gierer, S. Berking, H. Bode, C. N. David, K. Flick, G. Hansmann, H. Schaller, and E. Trenkner. Regeneration of hydra from reaggregated cells. Nature New Biology, 239:98--101, 1972.
• 11: Ulrich Hammel , Thomas Bäck, Evolution Strategies on Noisy Functions: How to Improve Convergence Properties, Proceedings of the International Conference on Evolutionary Computation. The Third Conference on Parallel Problem Solving from Nature: Parallel Problem Solving from Nature, p.159-168, October 09-14, 1994
• 12: Mark Herbster, Learning Additive Models Online with Fast Evaluating Kernels, Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory, p.444-460, July 16-19, 2001
• 13: Mark Herbster , Manfred K. Warmuth, Tracking the Best Expert, Machine Learning, v.32 n.2, p.151-178, Aug. 1998 [doi>10.1023/A:1007424614876]
• 14: Mark Herbster , Manfred K. Warmuth, Tracking the best linear predictor, The Journal of Machine Learning Research, 1, p.281-309, 9/1/2001
• 15: J. Herrmann. A genetic algorithm for minmax optimisation problems. volume 2, pages 1099--1103, 1999.
• 16: Kosuke Imamura , Terence Soule , Robert B. Heckendorn , James A. Foster, Behavioral Diversity and a Probabilistically Optimal GP Ensemble, Genetic Programming and Evolvable Machines, v.4 n.3, p.235-253, September 2003 [doi>10.1023/A:1025124423708]
• 17: E. Jordaan, A. Kordon, L. Chiang, and G. Smits. Robust inferential sensors based on ensemble of predictors generated by genetic programming. In X. Yao, E. Burke, J. A. Lozano, J. Smith, J. J. Merelo-Guervós, J. A. Bullinaria, J. Rowe, P. T. A. Kabán, and H.-P. Schwefel, editors, Parallel Problem Solving from Nature -- PPSN VIII, volume 3242 of LNCS, pages 522--531, Birmingham, UK, 18-22 Sept. 2004. Springer--Verlag.
• 18: H. Kitamo. Foundations of systems biology. MIT Press, ISBN 0-262-11266-3, 2001.
• 19: Proceedings of the Second International Workshop on Multiple Classifier Systems, July 2001
• 20: Ibrahim Kuscu, Promoting Generalisation of Learned Behaviours in Genetic Programming, Proceedings of the 5th International Conference on Parallel Problem Solving from Nature, p.491-500, September 27-30, 1998
• 21: I. Kuscu. Generalisation and domain specific functions in genetic programming. In Proceedings of the 2000 Congress on Evolutionary Computation CEC00, volume 2, pages 1393--1400, La Jolla Marriott Hotel La Jolla, California, USA, 6-9 July 2000. IEEE Press.
• 22: I. Kushchu. Genetic programming and evolutionary generalization. IEEE Transactions on Evolutionary Computation, 6(5): 431--442, October 2002.
• 23: Y. Liu, X. Yao, and T. Higuchi. Evolutionary ensembles with negative correlation learning. IEEE Transactions on Evolutionary Computation, 4(4): 380, 2000.
• 24: R. Lowenstein. When Genius Failed. Fourth Estate, 2002.
• 25: B. L. Miller and D. E. Goldberg. Genetic algorithms, selection scheme, and the varying effect of noise. Evolutionary Computation, 4(2):113--131, 1996.
• 26: J F. Miller. Evolving a self-repairing, self-regulating, french flag organism. pages 129--139, 2004.
• 27: F. W. Moore and O. N. Gacia. A new methodology for reducing brittleness in genetic programming. In Proceedings of the National Aerospace and Electronics 1997 Conferences, NAECON-97, 1997.
• 28: V. Nissen and J. Propach. On the robustness of population-based versus point-based optimisation in the presence of noise. IEEE Transactions on Evolutionary Computation, 2(3), 1998.
• 29: L. Panait and S. Luke. Methods for evolving robust programs. In Genetic and Evolutionary Computation -- GECCO 2003, volume 2724 of LNCS, pages 1740--1751. Springer, 2003.
• 30: Romesh Ranawana , Vasile Palade, Multi-Classifier Systems: Review and a roadmap for developers, International Journal of Hybrid Intelligent Systems, v.3 n.1, p.35-61, January 2006
• 31: W. F. Sharpe. The sharpe ratio. J. Portfolio Management, 21:49--58, 1994.
• 32: T. Soule. Voting teams: A cooperative approach to non-typical problems using genetic programming. In Proceedings of the Genetic and Evolutionary Computation Conference, volume~1, pages 916--922. Morgan Kaufmann, 1999.
• 33: T. Soule. Heterogeneity and specialization in evolving teams. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2000), pages 778--785. Morgan Kaufmann, 2000.
• 34: T. Soule. Operator choice and the evolution of robust solutions. In R. L. Riolo and B. Worzel, editors, Genetic Programming Theory and Practise, chapter 16, pages 257--270. Kluwer, 2003.
• 35: T. Soule, R. B. Heckendorn, and J. Shen. Solution stability in evolutionary computation. In N. Cicekli, editor, ISCIS XVII Seventeenth International Symposium On Computer and Information Sciences, pages 237--241, University of Central Florida, Orlando, Florida, Oct.28--30 2002. CRC Press.
• 36: Claudio De Stefano , Antonio Della Cioppa , Angelo Marcelli, Exploiting Reliability for Dynamic Selection of Classifiers by Means of Genetic Algorithms, Proceedings of the Seventh International Conference on Document Analysis and Recognition, p.671, August 03-06, 2003
• 37: S. Tsutsui and A. Ghosh. Genetic algorithms with a robust solution searching scheme. IEEE Transactions on Evolutionary Computation}, 1(3): 201--208, 1997.
• 38: A. Wagner. Robustness and Evolvability in Living Systems. Princeton University Press, 2005.
• 39: Byoung-Tak Zhang , Je-Gun Joung, Building Optimal Committees of Genetic Programs, Proceedings of the 6th International Conference on Parallel Problem Solving from Nature, p.231-240, September 18-20, 2000
• 40: M. Zhu and H. Chipman. Darwinian evolution in parallel universes: A parallel genetic algorithm for variable selection. Technometrics, 48(4):491--502, 2006.

INDEX TERMS

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

General Terms:
Algorithms, Experimentation

Keywords:
committee, diversity, dynamic environment, finance, genetic programming, robustness