Extracting Stock Multi-order Rules via Employing a Network Structure and Backward Q-Learning

Subject Areas : Journal of Investment Knowledge

Mohammad Reza Alimoradi ¹ , Ali Hosseinzadeh Kashan ²

1 - MS.c graduate of Financial Engineering, Department of Industrial and Systems Engineering, Tarbiat Modares University, Tehran, Iran.
2 - Assistant Professor, Department of Industrial and Systems Engineering, Tarbiat Modares University, Tehran, Iran. Corresponding Author

Received: 2017-12-24 Accepted : 2018-03-13 Published : 2019-06-22

Keywords: League championship algorithm, Multi-order rule, Technical Analysis, Reinforcement learning,

Abstract :

Traders in stock market consider stock information in the past few days as well as the current day information when making decision about selling or buying stock. To imitate stock traders’ style of decision-making, in this article, League Championship Algorithm (LCA) equipped with teams which have network structure has been introduced to extract multi-order rules. Multi-order rules would be extracted by LCA which not only contain the current day information, but also information of the previous days. Thus, a memory to store useful information has been created for each rule. To evaluate the model, 20 shares of companies in different industrial parts of Tehran stock exchange are used. In the testing simulation, the proposed model shows higher profits or lower losses than the buy & hold and genetic network programming models.  

References:

 

*      Bauer, R.J., 1994. Genetic algorithms and investment strategies. John Wiley & Sons.

*      Berutich, J.M., López, F., Luna, F. and Quintana, D., 2016. Robust technical trading strategies using GP for algorithmic portfolio selection. Expert Systems with Applications, 46, pp.307-315.

*      Bessembinder, H. and Chan, K., 1995. The profitability of technical trading rules in the Asian stock markets. Pacific-Basin Finance Journal, 3(2), pp.257-284.

*      Brock, W., Lakonishok, J. and LeBaron, B., 1992. Simple technical trading rules and the stochastic properties of stock returns. The Journal of finance, 47(5), pp.1731-1764.

*      Chang, P.C., Liao, T.W., Lin, J.J. and Fan, C.Y., 2011. A dynamic threshold decision system for stock trading signal detection. Applied Soft Computing, 11(5), pp.3998-4010.

*      Chen, Y., Mabu, S., Shimada, K. and Hirasawa, K., 2009. A genetic network programming with learning approach for enhanced stock trading model. Expert Systems with Applications, 36(10), pp.12537-12546.

*      Cheng, C.H., Chen, T.L. and Wei, L.Y., 2010. A hybrid model based on rough sets theory and genetic algorithms for stock price forecasting. Information Sciences, 180(9), pp.1610-1629.

*      Chien, Y.W.C. and Chen, Y.L., 2010. Mining associative classification rules with stock trading data–A GA-based method. Knowledge-Based Systems, 23(6), pp.605-614.

*      Cootner, P. H., 1967. The random character of stock market prices. Cambridge, Mass, M.I.T. Press.

*      Cunningham, S.W., 1973. The predictability of British stock market prices. Applied Statistics, 22(3), pp.315-331.

*      Dash, R. and Dash, P.K., 2016. A hybrid stock trading framework integrating technical analysis with machine learning techniques. The Journal of Finance and Data Science, 2, pp. 42-57.

*      Dryden, M.M., 1970. Filter tests of UK share prices. Applied Economics, 1(4), pp.261-275.

*      Esfahanipour, A. and Mousavi, S., 2011. A genetic programming model to generate risk-adjusted technical trading rules in stock markets. Expert Systems with Applications, 38(7), pp.8438-8445.

*      Fama, E.F. and Blume, M.E., 1966. Filter rules and stock-market trading. The Journal of Business, 39(1), pp.226-241.

*      Fama, E.F., 1970. Efficient capital markets: A review of theory and empirical work. The journal of Finance, 25(2), pp.383-417.

*      Givoly, D. and Lakonishok, J., 1979. The information content of financial analysts' forecasts of earnings: Some evidence on semi-strong inefficiency. Journal of Accounting and Economics, 1(3), pp.165-185.

*      Hudson, R., Dempsey, M. and Keasey, K., 1996. A note on the weak form efficiency of capital markets: The application of simple technical trading rules to UK stock prices-1935 to 1994. Journal of Banking & Finance, 20(6), pp.1121-1132.

*      Izumi, Y., Yamaguchi, T., Mabu, S., Hirasawa, K. and Hu, J., 2006, July. Trading rules on the stock markets using genetic network programming with candlestick chart. In 2006 IEEE International Conference on Evolutionary Computation (pp. 2362-2367). IEEE.

*      Jensen, M.C. and Benington, G.A., 1970. Random walks and technical theories: Some additional evidence. The Journal of Finance, 25(2), pp.469-482.

*      Kashan, A.H. and Karimi, B., 2010, July. A new algorithm for constrained optimization inspired by the sport league championships. In IEEE Congress on Evolutionary Computation (pp. 1-8). IEEE.

*      Kashan, A.H., 2009, December. League Championship Algorithm: A New Algorithm for Numerical Function Optimization. In SoCPaR (pp. 43-48).

*      Kashan, A.H., 2011. An efficient algorithm for constrained global optimization and application to mechanical engineering design: League championship algorithm (LCA). Computer-Aided Design, 43(12), pp.1769-1792.

*      Kashan, A.H., 2014. League Championship Algorithm (LCA): An algorithm for global optimization inspired by sport championships. Applied Soft Computing, 16, pp.171-200.

*      Kashan, A.H., Karimiyan, S., Karimiyan, M. and Kashan, M.H., 2012, November. A modified League Championship Algorithm for numerical function optimization via artificial modeling of the “between two halves analysis”. In Soft Computing and Intelligent Systems (SCIS) and 13th International Symposium on Advanced Intelligent Systems (ISIS), 2012 Joint 6th International Conference on (pp. 1944-1949). IEEE.

*      Mabu, S., Hirasawa, K., Obayashi, M. and Kuremoto, T., 2013. Enhanced decision making mechanism of rule-based genetic network programming for creating stock trading signals. Expert Systems with Applications, 40(16), pp.6311-6320.

*      Mabu, S., Obayashi, M. and Kuremoto, T., 2015. Ensemble learning of rule-based evolutionary algorithm using multi-layer perceptron for supporting decisions in stock trading problems. Applied Soft Computing, 36, pp.357-367.

*      Murphy, J. J., 1999. Technical analysis of the financial markets: a comprehensive guide to trading methods and applications. New York, New York Institute of Finance.

*      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, 32(4), pp.405-426.

*      Neely, C.J. and Weller, P.A., 1999. Technical trading rules in the European monetary system. Journal of International Money and Finance, 18(3), pp.429-458.

*      Nison, S., 2001. Japanese candlestick charting techniques: a contemporary guide to the ancient investment techniques of the Far East. New York, New York Institute of Finance.

*      Patel, M. (2010). Trading with Ichimoku clouds: the essential guide to Ichimoku Kinko Hyo technical analysis.

*      Sullivan, R., Timmermann, A. and White, H., 1999. Data‐snooping, technical trading rule performance, and the bootstrap. The journal of Finance, 54(5), pp.1647-1691.

*      Wang, L., Mabu, S., Ye, F. and Hirasawa, K., 2010, August. Generalized rule accumulation based on Genetic Network Programming considering different population size and rule length. In SICE Annual Conference 2010, Proceedings of (pp. 2631-2636). IEEE.

*      Wong, M.C.S., 1997. Fund management performance, trend-chasing technical analysis and investment horizons: a case study. Omega, 25(1), pp.57-63.