ABSTRACT
This paper extends current LCS research into financial time series forecasting by analysing the performance of agents utilising mathematical technical indicators for both environment classification and in selecting actions to be executed in the environment. It compares these agents with traditional models which only use such indicators to classify the environment and exit at the close of the next day. It is proposed that XCS agents utilising mathematical technical indicators for exit conditions will not only outperform similar agents which close the trade at the end of the next day, but also result in fewer trades and consequently lower commissions paid. The results show that in five out of six assets, agents using indicator exit conditions outperformed those exiting at the close of the next day, before commissions were factored in. After commissions are factored in, the performance gap between the two agent classes further widens. Additionally, the agent's best results are continuously able to outperform a buy and hold strategy.
- ]]Allen F. and Karjalainen R. (1999) Using Genetic Algorithms to find technical trading rules. Journal of Financial Economics, 51(2):245--271, 1999.Google ScholarCross Ref
- ]]Beltrametti L., Fiorentini R., Marengo L., and Tamborini R. (1997) A learning-to-forecast experiment on the foreign exchange market with a Classifier System. Journal of Economic Dynamics and Control, 21(8{9):1543--1575, 1997.Google Scholar
- ]]Butz, M., Sastry, K. and Goldberg, D. (2005) Strong, Stable, and Reliable Fitness Pressure in XCS due to Tournament Selection. Genetic Programming and Evolvable Machines v.6 n.1, pages 53--77. Google ScholarDigital Library
- ]]Brock, W. Lakonishock J and LeBaron B. (1992) Simple Technical Trading Rules and the Stochastic Properties of Stock Returns. Journal of Finance 47. Pages 1731--1764.Google Scholar
- ]]Chen, S.-H (2002) Genetic Algorithms and Genetic Programming in Computational Finance. Kluwer Academic Publishers, Norwell, MA, 2002. Google ScholarDigital Library
- ]]Detry, P.J. and Grégoire, P. (2001) Other evidences of the predictive power of technical analysis: the moving average rules on European indexes. In Proceedings of the Lugano European Financial Management Association Conference.Google ScholarCross Ref
- ]]Dewachter, H. (2001) Can Markov switching models replicate chartist profits in the foreign exchange market? Journal of International Money and Finance, Elsevier, vol. 20(1), Pages 25--41, February.Google ScholarCross Ref
- ]]Dooley, M. and Schaffer, J. (1983) Analysis of Short-Run Exchange Rate Behavior: March 1973 to November 1981. In Bigman, D. and Taya, T. Floating Exchange Rates and State of World Trade and Payments, 43--70, Ballinger Publishing Company, Cambridge, Mass (1984).Google Scholar
- ]]Gershoff, M. (2006) An investigation of HXCS Traders. In School of Informatics. Vol. Master of Sciences Edinburgh: University of Edinburgh.Google Scholar
- ]]Holland, J. (1975) Adaptation in Natural and Artificial Systems. University of Michigan Press. Google ScholarDigital Library
- ]]Kalyvas, E. (2001) Using Neural Networks and Genetic Algorithms to Predict Stock Market Returns. University of Manchester Master of Science thesis.Google Scholar
- ]]Levich, R. and Thomas, L. (1993). The Merits of Active Currency Management: Evidence from International Bond Portfolios. Financial Analysts Journal 49, No. 5.Google Scholar
- ]]Mahfoud, S. and Mani, G. (1996) Financial forecasting using Genetic Algorithms. Applied Artificial Intelligence, 10(6):543--565, 1996.Google ScholarCross Ref
- ]]Neely, C., Weller, P. and Dittmar, R. (1997) Is Technical Analysis in the Foreign Exchange Market Profitable? A Genetic Programming Approach. Journal of Financial and Quantitative Analysis, December 1997.Google ScholarCross Ref
- ]]Okunev, J. and White, D. (2003) Do momentum-based strategies still work in foreign currency markets? Journal of Financial and Quantitative Analysis 38. Pages 425--447.Google ScholarCross Ref
- ]]Olson, D. (2004) Have trading rule profits in the currency market declined over time? Journal of Banking and Finance 28. Pages 85--105.Google ScholarCross Ref
- ]]Schulenburg, S. and Ross, P. (2001) An Adaptive Agent Based Economic Model. In Lanzi P. L. et al. Advances in Learning Classifier Systems. Proceedings of the Third International Workshop (IWLCS-2000). Volume LNAI-1996 of Lecture Notes in Aritifical Inteligence, Berlin, 2001. Springer. Pages 265--284.Google Scholar
- ]]Schulenburg, S. and Ross, P. (2001) Strength and money: An LCS approach to increasing returns. In Lanzi P. L. et al. Advances in Learning Classifier Systems. Proceedings of the Third International Workshop (IWLCS-2000). Volume LNAI-1996 of Lecture Notes in Aritifical Inteligence, Berlin, 2001. Springer. Pages 114--137. Google ScholarDigital Library
- ]]Schulenburg, S. and Ross, P. (2002) Explorations in LCS models of stock trading. In P.L. Lanzi, W. Stolzmann, and S.W. Wilson, editors, Advances in Learning Classifier Systems. Proceedings of the Fourth International Workshop (IWLCS-2001), volume LNAI-2321 of Lecture Notes in Artificial Intelligence, pages 151--180, Berlin, 2002. Springer. Google ScholarDigital Library
- ]]Schulenburg, S. and Wong, S.Y. (2007) Portfolio allocation using XCS experts in technical analysis, market conditions and options market. Genetic And Evolutionary Computation Conference archive. Proceedings of the 2007 GECCO. Google ScholarDigital Library
- ]]Srinivasa, K.G., Venugopal, K.R. and Patnaik, L.M. (2006) An efficient fuzzy based neuro: genetic algorithm for stock market prediction. International Journal of Hybrid Intelligent Systems archive Volume 3, Issue 2. Pages 63--81. Google ScholarDigital Library
- ]]Steiner, M. and Wittkemper, H.G. (1996). Neural networks as an alternative stock market model. In Refenes, A. P. Neural networks in the capital markets. John Wiley and Sons. Pages 137--149.Google Scholar
- ]]Stone, C. and Bull, L. (2008) Foreign Exchange Trading using a Learning Classifier System. Studies in Computational Intelligence (SCI) 125, 169--189. Springer-Verlag.Google Scholar
- ]]Sweeney, R.J. (1986) Beating the foreign exchange market. Journal of Finance 41. Pages 163--182.Google Scholar
- ]]Tsibouris, G. and Zeidenberg, M. (1996) Testing the Efficient Market Hypothesis with Gradient Descent Algorithms. Pages 127--136. John Wiley and Sons Ltd.Google Scholar
- ]]Wilson, S.W. (1994) ZCS: A Zeroth Level Classifier. Evolutionary Computation, 2:1--18 Google ScholarDigital Library
- ]]Wilson, S.W. (1995) Classifier Fitness Based on Accuracy. Evolutionary Computation, 3(2):149--175. Google ScholarDigital Library
Index Terms
- An XCS approach to forecasting financial time series
Recommendations
Portfolio allocation using XCS experts in technical analysis, market conditions and options market
GECCO '07: Proceedings of the 9th annual conference companion on Genetic and evolutionary computationSchulenburg (2000) first proposed the idea to model different trader types by supplying different input information sets to a group of homogenous LCS agent. Gershoff (2006) investigated this idea further with XCS agent. This paper takes an extra step to ...
The Volatility for Pre and Post Global Financial Crisis: An Application of Computational Finance
The asymmetric volatility, temporary volatility, and permanent volatility of financial asset returns have attracted much interest in recent years. However, a consensus has not yet been reached on the causes of them for both the stocks and markets. This ...
Using the XCS classifier system for portfolio allocation of MSCI index component stocks
In a recent study, Schulenburg and Ross (2001) proposed the LCS for short-term stock forecast. Studley and Bull (2007) proposed the extended classifier system (XCS) agent to model different traders by supplying different input information. Announcement ...
Comments