Generating Investment Strategies Using Multiobjective Genetic Programming and Internet Term Popularity Data

Martin Jakubéci


Searching for stock picking strategies can be modelled as a multiobjective optimization problem. The objectives are mostly the profit and risk. Because of the conflicting nature of these objectives, we have to find pareto optimal solutions. Multiobjective genetic programming (MOGP) can be used to find tree based solutions, using evolutionary operators. The advantage is that this algorithm can combine any number of inputs and generate complex models. Recent research shows, that the popularity of different terms on the internet can be used to enhance the models. This paper deals with a SPEA2 MOGP implementation, which uses Google trends and Wikipedia popularity to find stock investment strategies.

Full text: PDF


genetic programming, Google trends, stock

JEL Codes

G11 - Portfolio Choice, Investment Decisions.


Alexander, C., 2008. Quantitative methods in finance. Chichester: John Wiley and Sons, Ltd.

Allen, F., and Karjalainen, R., 1999. Using genetic algorithms to find technical trading rules. Journal of Financial Economics, 51, 245–271.

Beechey, M., Gruen, D., and Vickery, J., 2000. The efficient market hypothesis: a survey: Reserve Bank of Australia,.

Bohdalová, M., and Greguš, M., 2011. The identification of key market risk factors for a portfolio of EU bonds. Global business and economics anthology, 2(2), 470-477.

Bohdalová, M., and Greguš, M., 2012. Portfolio optimization and Sharpe ratio based on copula approach. Research Journal of Economics, Business and ICT, 6, 6-10.

Bradshaw, N. A., Walshaw, C., Ierotheou, C., and Parrott, A. K., 2009. A Multi-Objective Evolutionary Algorithm for Portfolio Optimisation. Proceedings of the Adaptive and Emergent Behaviour and Complex Systems Convention, 27–32.

Chen, S. H., and Navet, N., 2007. Failure of Genetic-Programming Induced Trading Strategies: Distinguishing between Efficient Markets and Inefficient Algorithms. Computational Intelligence in Economics and Finance, 2, 169-182.

Chen, S. S., Huang, C. F., and Hong, T. P., 2014. An Improved Multi-Objective Genetic Model for Stock Selection with Domain Knowledge. Technologies and Applications of Artificial Intelligence, Lecture Notes in Computer Science, 8916, 66-73.

Chovancová, B., 2006. Finančnýtrh – nástroje, transakcieainštitúcie. Bratislava: Iura Edition.

Hassan, G. N. A., 2010. Multiobjective genetic programming for financial portfolio management in dynamic environments. (Doctoral thesis), University College London.

Karabulut, Y., 2013. Can Facebook Predict Stock Market Activity? , Goethe University Frankfurt.

Lohpetch, D., and Corne, D., 2011. Multiobjective algorithms for financial trading: Multiobjective out-trades single-objective. IEEE Congress on Evolutionary Computation, 192–199.

Metalinq, 2014. MetaLinq - LINQ to Expressions. from

Moat, H. S., Curme, C., Avakian, A., Kenett, D. Y., Stanley, H. E., and Preis, T., 2013. Quantifying Wikipedia Usage Patterns Before Stock Market Moves. Scientific Reports, 3.

Poli, R., Langdon, W. B., and McPhee, N. F., 2008. A Field Guide to Genetic Programming. Retrieved 25 March, 2014, from

Potvin, J. Y., Soriano, P., and Vallée, M., 2004. Generating trading rules on the stock markets with genetic programming. Computers & Operations Research, 31(7), 1033–1047.

Preis, T., Moat, H. S., and Stanley, H. E., 2013. Quantifying Trading Behavior in Financial Markets Using Google Trends. Scientific Reports, 3.

Ruiz, J. E., Hristidis, V., Castillo, C., Gionis, A., and Jaimes, A., 2012. Correlating Financial Time Series with Micro-Blogging Activity. Paper presented at the WSDM’12, Seattle, WA.

Skolpadungket, P., Keshav, D., and Harnpornchai, N., 2007. Portfolio Optimization using Multi-objective Genetic Algorithms. IEEE Congress on Evolutionary Computation, 516 - 523.

Thomsett, M. C., 2006. Getting started in fundamental analysis. Hoboken: John Wiley & Sons, Inc.

Toman, R., 2008. Analýza faktorového portfolio najviac likvidných cenných papierov na BCCP v závislosti na HDP, inflácii a PX. (Master's thesis), Masaryk University, Brno.

Zitzler, E., Laumanns, M., and Thiele, L., 2001. SPEA2: Improving the Strength Pareto Evolutionary Algorithm. Evolutionary Methods for Design, Optimization, and Control, 95–100.