Genetic programming for quantitative stock selection

ABSTRACT

We provide an overview of using genetic programming (GP) to model stock returns. Our models employ GP terminals (model decision variables) that are financial factors identified by experts. We describe the multi-stage training, testing and validation process that we have integrated with GP selection to be appropriate for financial panel data and how the GP solutions are situated within a portfolio selection strategy. We share our experience with the pros and cons of evolved linear and non-linear models, and outline how we have used GP extensions to balance different objectives of portfolio managers and control the complexity of evolved models.

REFERENCES

• 1: Allen, F. and Kajalainen, R. (1999). Using genetic algorithms to find technical trading rules. Journal of Financial Economics, 51:245--271.
• 2: Barthelemy, Sylvain and Apoteker, Thierry, Genetic Algorithms and Financial Crises in Emerging Markets(May 2000). CEFI International Conference Proceedings. Available at SSRN: http://ssrn.com/abstract=687741
• 3: Becker, Ying L, Fei, Peng, and Lester, Anna M. (2006). Stock selection: An innovative application of genetic programming methodology. In Riolo, Rick L., Soule, Terence, and Worzel, Bill, editors, Genetic Programming Theory and Practice IV, volume 5 of Genetic and Evolutionary Computation, chapter 19, pages 315--334. Springer, Ann Arbor.
• 4: Becker,Ying L., Fox,Harold, and Fei, Peng (2007). An empirical study of multi objective algorithms for stock ranking. In Riolo, Rick L., Soule, Terence, and Worzel, Bill, editors, Genetic Programming Theory and Practice V, Genetic and Evolutionary Computation, chapter 14, pages 239--259. Springer, Ann Arbor.
• 5: Caplan, Michael and Becker, Ying (2004). Lessons learned using genetic programming in a stock picking context. In O'Reilly, Una-May, Yu, Tina, Riolo, RickL., and Worzel, Bill, editors, Genetic Programming Theory and Practice II, chapter 6, pages 87--102. Springer, Ann Arbor.
• 6: Chen, Shu-Heng and Yeh, Chia-Hsuan (1997) Toward a computable approach to the efficient market hypothesis: An application of genetic programming, Journal of Economic Dynamics and Control, Volume 21, Issue 6, 1 June 1997, Pages 1043--1063, Society of Computational Economics Conference
• 7: Fama, E.F. and French,K.R. (1992).The cross-section of expected stock returns. Journal of Finance, 47:427--465.
• 8: John H. Holland, Adaptation in natural and artificial systems, MIT Press, Cambridge, MA, 1992
• 9: Kaboudan, M. A. (2001). Genetically evolved models and normality of their fitted residuals. Journal of Economic Dynamics and Control, 25(11):1719--1749.
• 10: Karunamurthy, Vijay (2003). A genetic programming approach to the dynamic portfolio rebalancing problem. In Koza, John R., editor, Genetic Algorithms and Genetic Programming at Stanford 2003, pages 100--108. Stanford Bookstore, Stanford, California, 94305-3079 USA.
• 11: Kim, Minkyu, Becker, YingL., Fei, Peng, and O'Reilly, Una-May (2008). Constrained genetic programming to minimize overfitting in stock selection. In Riolo, Rick L., Soule, Terence, and Worzel, Bill, editors, Genetic Programming Theory and Practice VI, chapter 12, pages 179--194. Springer, Ann Arbor.
• 12: Korns, Michael F. (2006) Large-Scale, Time-Constrained Symbolic Regression. In Riolo, Rick L., Soule, Terence, and Worzel, Bill, editors, Genetic Programming Theory and Practice VI, chapter 16. Springer, Ann Arbor
• 13: John R. Koza, Genetic programming: on the programming of computers by means of natural selection, MIT Press, Cambridge, MA, 1992
• 14: C. Lawrenz , F. Westerhoff, Modeling Exchange Rate Behaviorwith a Genetic Algorithm, Computational Economics, v.21 n.3, p.209-229, June 2003 [doi>10.1023/A:1023943726237]
• 15: Jin Li , Edward P. K. Tsang, Improving Technical Analysis Predictions: An Application of Genetic Programming, Proceedings of the Twelfth International Florida Artificial Intelligence Research Society Conference, p.108-112, May 01-05, 1999
• 16: Neely, Christopher J., Weller, Paul A., and Dittmar, Rob (1997). Is technical analysis in the foreign exchange market profitable? A genetic programming approach. The Journal of Financial and Quantitative Analysis, 32(4):405--426.
• 17: Ross, S. (1976). The arbitrage theory of capital asset pricing. Journal of Economic Theory, 13:341--360.
• 18: Sharpe,W.F. (1964). Capital asset prices: A theory of market equilibrium under conditions of risk. Journal of Finance, 19(3):425--442.
• 19: Thomas, J.D and K. Sycara (1999). The Importance of Simplicity and Validation in Genetic Programming for Data Mining in Financial Data. In Freitas, editor, Data Mining with Evolutionary Algorithms: Research Directions, AAAI Press.
• 20: Wagman, Liad (2003). Stock portfolio evaluation: An application of genetic programming-based technical analysis. In Koza, John R., editor, Genetic Algorithms and Genetic Programming at Stanford 2003, pages 213--220.
• 21: Wang, J. (2000). Trading and hedging in s&p 500 spot and futures markets using genetic programming. Journal of Futures Markets, 20(10):911--942.
• 22: Zhou, A. (2003). Enhanced emerging market stock selection. In Genetic Programming and Practice I. chapter 18, pages 291--302. Kluwer.

INDEX TERMS

Primary Classification:
  J. Computer Applications
  J.1 ADMINISTRATIVE DATA PROCESSING
      Subjects: Business

General Terms:
Algorithms, Economics

Keywords:
"genetic programming", genetic algorithm, quantitative asset management, stock selection, symbolic regression