Skip to main content
SpringerLink
Log in

Evolving robust GP solutions for hedge fund stock selection in emerging markets

  • Focus
  • Published:
Soft Computing Aims and scope Submit manuscript

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 two new approaches. The first approach uses subsets of extreme environments during training and the second approach uses a voting committee of GP individuals with differing phenotypic behaviour.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Notes

  1. An alternative approach is to look for an adaptive solution, i.e. one that detects changes in the environment and responds by modifying its internal structure and the way that it operates. However, a similar question arises: in an unforgiving environment, would it have time to adapt and survive without prior exposure to extreme environments?

  2. Connected networks of RNA sequences with identical structure.

  3. A contrarian strategy might do the opposite—sell the high stocks and buy the low stocks, on the expectation that mean-reversion will occur and the high stocks will fall while the low stocks will rise.

References

  • Aragón VS, Esquivel SC (2004) An evolutionary algorithm to track changes of optimum value locations in dynamic environments. J Comput Sci Technol 4(3):127–134

    Google Scholar 

  • Bersano-Begey TF, Daida JM (1997) A discussion on generality and robustness and a framework for fitness set construction in genetic programming to promote robustness. In: Koza JR (ed) Late breaking papers at the 1997 genetic programming conference. Stanford Bookstore, Stanford University, California, pp 11–18

  • Bowers CP (2005) Formation of modules in a computational model of embryogeny. In: The 2005 IEEE Congress on evolutionary computation, vol 1, pp 537–542

  • Branke J (1998) Creating robust solutions by means of evolutionary algorithms. In: PPSN V: Proceedings of the 5th international conference on parallel problem solving from nature. Springer-Verlag, London, pp 119–128

  • Brown G, Wyatt J, Harris R, Yao X (2005) Diversity creation methods: a survey and categorisation. Inf Fusion 6(1):5–20

    Article  Google Scholar 

  • Buxton B, Langdon WB, Barrett SJ (2001) Data fusion by intelligent classifier combination. Meas Control 34(8):229–234

    Google Scholar 

  • Dietterich TG (2000) Ensemble methods in machine learning. In: Proceedings of the first international workshop on multiple classifier systems. LNCS, vol 1857. Springer, New York, pp 1–15

  • Egan JP (1975) Signal detection theory and ROC analysis. Academic Press, New York

  • Fitzpatrick JM, Grefenstette JJ (1988) Genetic algorithms in noisy environments. Mach Learn 3:101–120

    Google Scholar 

  • Gagné C, Schoenauer M, Parizeau M, Tomassini M (2006) Genetic programming, validation sets, and parsimony pressure. In: Collet P, Tomassini M, Ebner M, Gustafson S, Ekárt A (eds) Proceedings of the 9th European conference on genetic programming. Lecture notes in computer science, vol 3905. Springer, Budapest, pp 109–120. http://link.springer.de/link/service/series/0558/papers/3905/39050109.pdf

  • Gierer A, Berking S, Bode H, David CN, Flick K, Hansmann G, Schaller H, Trenkner E (1972) Regeneration of hydra from reaggregated cells. Nat New Biol 239:98–101

    Article  Google Scholar 

  • Hammel U, Bäck T (1994) Evolution strategies on noisy functions: How to improve convergence properties. In: Davidor Y, Schwefel HP, Männer R (eds) Proceedings of the international conference on evolutionary computation, the third conference on parallel problem solving from nature (PPSN III), vol 866. Springer, Jerusalem, pp 159–168. http://citeseer.ist.psu.edu/hammel94evolution.html

  • Haynes T, Wainwright R, Sen S, Schoenefeld D (1995) Strongly typed genetic programming in evolving cooperation strategies. In: Eshelman L (ed) Genetic algorithms: Proceedings of the sixth international conference (ICGA95). Morgan Kaufmann, Pittsburgh, pp 271–278. http://www.mcs.utulsa.edu/~rogerw/papers/Haynes-icga95.pdf

  • Herbster M (2001) Learning additive models online with fast evaluating kernels. In: Proceedings of the 14th annual conference on computational learning theory and and 5th European conference on computational learning theory. LNCS, vol 2111. Springer, New York, pp 444–460

  • Herbster M, Warmuth MK (1998) Tracking the best expert. Mach Learn 32(2):151–178

    Article  MATH  Google Scholar 

  • Herbster M, Warmuth MK (2001) Tracking the best linear predictor. J Mach Learn Res 1:281–309

    Article  MATH  MathSciNet  Google Scholar 

  • Herrmann J (1999) A genetic algorithm for minimax optimization problems. In: Proceedings of the Congress on evolutionary computation, vol 2, pp 1099–1103

  • Huynen M, Stadler P, Fontana W (1996) Smoothness within ruggedness: the role of neutrality in adaptation

  • Imamura K, Soule T, Heckendorn R, Foster J (2003) Behavioral diversity and a probabilistically optimal GP ensemble. Genet Program Evolvable Mach 4:235–253

    Article  Google Scholar 

  • Ito T, Iba H, Kimura M (1996) Robustness of robot programs generated by genetic programming. In: Koza JR, Goldberg DE, Fogel DB, Riolo RL (eds) Genetic Programming 1996: Proceedings of the first annual conference. MIT Press, Stanford University, California, pp 321–326

    Google Scholar 

  • Jordaan E, Kordon A, Chiang L, Smits G (2004) Robust inferential sensors based on ensemble of predictors generated by genetic programming. In: Yao X, Burke E, Lozano JA, Smith J, Merelo-Guervós JJ, Bullinaria JA, Rowe J, Kabán PTA, Schwefel HP (eds) Parallel problem solving from nature—PPSN VIII. LNCS, vol 3242. Springer-Verlag, Birmingham, pp 522–531. doi:10.1007/b100601. http://www.springerlink.com/openurl.asp?genre=article&issn=0302-9743&volume=3242&spage=522

  • Kitamo H (2001) Foundations of systems biology. MIT Press, Cambridge. ISBN: 0-262-11266-3

  • Kittler J, Roli F (2001) Multiple classifier systems. In: Proceedings of 2nd international workshop, MCS2001. Springer-Verlag, New York

  • Kuscu I (1998) Promoting generalization of learned behaviours in genetic programming. In: Eiben AE, Back T, Schoenauer M, Schwefel HP (eds) Fifth international conference on parallel problem solving from nature. LNCS, vol 1498. Springer-Verlag, Amsterdam, pp 491–500

  • Kuscu I (2000) Generalisation and domain specific functions in genetic programming. In: Proceedings of the 2000 Congress on evolutionary computation CEC00. IEEE Press, La Jolla Marriott Hotel La Jolla, California, USA, vol 2, pp 1393–1400. doi:10.1109/CEC.2000.870815. http://citeseer.ist.psu.edu/502977.html

  • Kushchu I (2002) Genetic programming and evolutionary generalization. IEEE Trans Evol Comput 6(5):431–442

    Article  Google Scholar 

  • Liu Y, Yao X, Higuchi T (2000) Evolutionary ensembles with negative correlation learning. IEEE Trans Evol Comput 4(4):380. http://citeseer.ist.psu.edu/article/liu00evolutionary.html

    Google Scholar 

  • Lowenstein R (2002) When genius failed. Fourth Estate

  • Miller JF (2004) Evolving a self-repairing, self-regulating, french flag organism. In: GECCO 2004, pp 129–139

  • Miller BL, Goldberg DE (1996) Genetic algorithms, selection scheme, and the varying effect of noise. Evol Comput 4(2):113–131

    Article  Google Scholar 

  • Moore FW, Garcia ON (1997) A new methodology for reducing brittleness in genetic programming. In: Proceedings of the National Aerospace and Electronics 1997 conferences, NAECON-97

  • Nissen V, Propach J (1998) On the robustness of population-based versus point-based optimisation in the presence of noise. IEEE Trans Evol Comput 2(3):107–119

    Google Scholar 

  • Panait L, Luke S (2003) Methods for evolving robust programs. In: Genetic and evolutionary computation—GECCO 2003. LNCS, vol 2724. Springer, New York, pp 1740–1751

  • Ranawana R, Palade V (2006) Multi-classifier systems: review and a roadmap for developers. Int J Hybrid Intell Syst 3(1):35–61

    MATH  Google Scholar 

  • Reynolds CW (1992) An evolved, vision-based behavioral model of coordinated group motion. In: Meyer JA, Wilson SW (eds) From animals to animats (Proceedings of simulation of adaptive behaviour). MIT Press, Cambridge

  • Rosca J (1996) Generality versus size in genetic programming. In: Koza JR, Goldberg DE, Fogel DB, Riolo RL (eds) Genetic Programming 1996: Proceedings of the first annual conference. MIT Press, Cambridge, pp 381–387

  • Sharpe WF (1994) The Sharpe ratio. J Portf Manag 21:49–58

    Article  Google Scholar 

  • Soule T (1999) Voting teams: a cooperative approach to non-typical problems using genetic programming. In: Proceedings of the genetic and evolutionary computation conference. Morgan Kaufmann, vol 1, pp 916–922. http://www.cs.uidaho.edu/tsoule/research/vote2.ps

  • Soule T (2000) Heterogeneity and specialization in evolving teams. In: Proceedings of the genetic and evolutionary computation conference (GECCO-2000). Morgan Kaufmann, pp. 778–785. http://www.cs.bham.ac.uk/~wbl/biblio/gecco2000/ESO56.ps

  • Soule T (2003) Operator choice and the evolution of robust solutions. In: Riolo RL, Worzel B (eds) Genetic programming theory and practise, chap 16. Kluwer, Dordrecht, pp 257–270

  • Soule T, Heckendorn RB, Shen J (2002) Solution stability in evolutionary computation. In: Cicekli N (ed) ISCIS XVII seventeenth international symposium on computer and information sciences. CRC Press, University of Central Florida, Orlando, pp 237–241

  • Stefano CD, Cioppa AD, Marcelli A (2003) Exploiting reliability for dynamic selection of classifiers by means of genetic algorithms. In: ICDAR ’03: Proceedings of the seventh international conference on document analysis and recognition. IEEE Computer Society, Washington, pp 671–675

  • Tsutsui S, Ghosh A (1997) Genetic algorithms with a robust solution searching scheme. IEEE Trans Evol Comput 1(3):201–208

    Article  Google Scholar 

  • Wagner A (2005) Robustness and evolvability in living systems. Princeton University Press, Princeton

  • Zhang BT, Joung JG (2000) Building optimal committees of genetic programs. In: Schoenauer M, Deb K, Rudolph G, Yao X, Lutton E, Merelo JJ, Schwefel HP (eds) Parallel problem solving from nature—PPSN VI. Springer, Berlin, pp 231–240. http://citeseer.ist.psu.edu/zhang00building.html

  • Zhu M, Chipman H (2006) Darwinian evolution in parallel universes: a parallel genetic algorithm for variable selection. Technometrics 48(4):491–502

    Article  MathSciNet  Google Scholar 

Download references

Acknowledgments

The authors thank Dr Gerard Vila and Prospect Wealth Management for suggestions and discussions, SIAM Capital for financial support, and Reuters for access to financial data. We also thank the anonymous referees for their helpful comments.

Author information

Authors and Affiliations

  1. Department of Computer Science, University College London, Gower Street, London, WC1E 6BT, UK

    Wei Yan

  2. Financial Computing, Department of Computer Science, University College London, Gower Street, London, WC1E 6BT, UK

    Christopher D. Clack

Authors
  1. Wei Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Christopher D. Clack
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Christopher D. Clack.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Yan, W., Clack, C.D. Evolving robust GP solutions for hedge fund stock selection in emerging markets. Soft Comput 15, 37–50 (2011). https://doi.org/10.1007/s00500-009-0511-4

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-009-0511-4

Keywords

Search

Navigation