Abstract
Over the last decade, numerous papers have investigated the use of Genetic Programming (GP) for creating financial trading strategies. Typically, in the literature, the results are inconclusive but the investigators always suggest the possibility of further improvements, leaving the conclusion regarding the effectiveness of GP undecided. In this paper, we discuss a series of pretests aimed at giving more clear-cut answers as to whether GP can be effective with the training data at hand. Precisely, pretesting allows us to distinguish between a failure due to the market being efficient or due to GP being inefficient. The basic idea here is to compare GP with several variants of random searches and random trading behaviors having well-defined characteristics. In particular, if the outcomes of the pretests reveal no statistical evidence that GP possesses a predictive ability superior to a random search or a random trading behavior, then this suggests to us that there is no point in investing further resources in GP. The analysis is illustrated with GP-evolved strategies for nine markets exhibiting various trends.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Allen F, Karjalainen R (1999) Using genetic algorithms to find technical trading rules. Journal of Financial Economics 51:245–271
Boffetta G, Cencini M, Falcioni M, Vulpiani A (2002) Predictability: A way to characterize complexity. Physics Reports 356:367
Chen SH, Kuo TW (2003) Overfitting or poor learning: a critique of current financial applications of GP. In: Ryan C, Soule T, Keijzer M, Tsang E, Poli R, Costa E (eds) Proceedings of the sixth European conference on genetic programming. Springer-Verlag:34–46
Chen SH, Kuo TW, Hoi KM (2007) Genetic programming and financial trading: how much about “what we know”? In: Zopounidis C, Doumpos M, Pardalos PM (eds) Handbook of financial engineering. Springer. Forthcoming.
Danilov D, Magnus J (2004) Forecast accuracy after pretesting with an application to the stock market. Journal of Forecasting 23:251–274
del Arco-Calderón CL, Viñuela PI, Castro JCH (2004) Forecasting time series by means of evolutionary algorithms. In: PPSN:1061–1070
Gagné C, Parizeau M (2002) Open beagle: a new versatile c++ framework for evolutionary computations. In: Late breaking papers, genetic and evolutionary computing conference (GECCO):161–168
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. Springer Verlag:109–120
Giles J, Giles D (1993) Pre-test estimation and testing in econometrics: recent developments. Journal of Economic Surveys 7(2):145–197
Hong J, Chung Y (2003) Are the directions of stock price changes predictable? Statistical theory and evidence. Technical report, Cornell University
Kaboudan MA (1999) A measure of time series’ predictability using genetic programming applied to stock returns. Journal of Forecasting 18:345–357
Kaboudan MA (2000) Evaluation of forecasts produced by genetically evolved models. In: 6th international conference on computing in economics and finance. Society for Computational Economics
Langdon WB, Poli R (2002) Foundations of genetic programming. Springer-Verlag.
Li J, Tsang E (2000) Reducing failures in investment recommendations using genetic programming. In: 6th international conference on computing in economics and finance. Society for Computational Economics
Neely C, Weller P, Dittmar R (1997) Is technical analysis in the foreign exchange market profitable? A genetic programming approach. Journal of Financial and Quantitative Analysis 32(4):405–427
Palus M, Pecen L, Pivka D (1995) Estimating predictability: redundancy and surrogate data method. Working Paper 95-07-060, Santa Fe Institute. available at http://ideas.repec.org/p/wop/safiwp/95-07-060.html
Santini M, Tettamanzi A (2001) Genetic programming for financial time series prediction. In: Miller J, Tomassini M, Lanzi PL, Ryan C, Tettamanzi AGB, Langdon WB (eds) Proceedings of the fourth European conference on genetic programming. Springer Verlag:361–370
Schreiber T, Schmitz A (2000) Surrogate time series. Phys. D 142(3–4):346–382
Shalizi CR (2006) Methods and techniques of complex systems science: an overview. In: Deisboeck T, Yasha K (eds) Complex systems science in biomedicine. Springer Verlag, New York:33–114
Sullivan R, Timmermann A, White H (1999) Data-snooping, technical trading rule performance, and the bootstrap. Journal of Finance 54:1647–1692
Zumbach G, Pictet O, Masutti O (2001) Genetic programming with syntactic restrictions applied to financial volatility forecasting. Technical Report GOZ.2000-07-28, Olsen & Associates.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Chen, SH., Navet, N. (2007). Failure of Genetic-Programming Induced Trading Strategies: Distinguishing between Efficient Markets and Inefficient Algorithms. In: Chen, SH., Wang, P.P., Kuo, TW. (eds) Computational Intelligence in Economics and Finance. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-72821-4_11
Download citation
DOI: https://doi.org/10.1007/978-3-540-72821-4_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-72820-7
Online ISBN: 978-3-540-72821-4
eBook Packages: Computer ScienceComputer Science (R0)