Abstract
Several machine learning paradigms have been applied to financial forecasting, attempting to predict the market’s behavior, with the final objective of profiting from trading shares. While anticipating the performance of such a complex system is far from trivial, this issue becomes even harder when the investors do not have large amounts of money available. In this paper, we present an evolutionary portfolio optimizer for the management of small budgets. The expected returns are modeled resorting to Multi-layer Perceptrons, trained on past market data, and the portfolio composition is chosen by approximating the solution to a multi-objective constrained problem. An investment simulator is then used to measure the portfolio performance. The proposed approach is tested on real-world data from Milan stock exchange, exploiting information from January 2000 to June 2010 to train the framework, and data from July 2010 to August 2011 to validate it. The presented tool is finally proven able to obtain a more than satisfying profit for the considered time frame.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
Obtaining the desired quantity at the wished price might not always be possible.
- 3.
In the real world, sometimes it is impossible to sell a stock in time, and as a result an investor might not have money available to buy another desired one.
- 4.
In a real market, a stock that has a bid-ask spread too wide could be suspended from the negotiation, and goes to auction, depending on market regulations.
- 5.
FTSE-all share, 03/06/2010-02/08/2011. During this time frame, the index had considerable fluctuations, ranging from a maximum of 21600 reached before October 2010 to a fall to 19105 in November, up to a quote of 23167 in February 2011, and a final decrease to a minimum of 17270.
- 6.
http://www.itcup.it/, known as Top Trader Cup in 2011.
References
Graham, B., Dodd, D.L.: Security analysis. McGraw-Hill New, York (2008)
Sheppard, K.: Financial econometrics notes. University of Oxford, New York (2010)
Bodie, Z., Kane, A., Marcus, A.J.: Investments (2014)
Markowitz, H.: Portfolio selection*. J. Finan. 7(1), 77–91 (1952)
Markowitz, H.M.: Portfolio selection: efficient diversification of investments. Yale University Press, New Haven (1968)
Swisher, P., Kasten, G.W.: Post-modern portfolio theory. J. Finan. Plann. Denver 18(9), 74 (2005)
Shefrin, H., Statman, M.: Behavioral portfolio theory. J. Finan. Quant. Anal. 35(02), 127–151 (2000)
Oberlechner, T.: Importance of technical and fundamental analysis in the european foreign exchange market. Int. J. Finan. Econ. 6(1), 81–93 (2001)
Abarbanell, J.S., Bushee, B.J.: Fundamental analysis, future earnings, and stock prices. J. Account. Res. 35, 1–24 (1997)
Dechow, P.M., Hutton, A.P., Meulbroek, L., Sloan, R.G.: Short-sellers, fundamental analysis, and stock returns. J. Finan. Econ. 61(1), 77–106 (2001)
Edwards, R.D., Magee, J., Bassetti, W.: Technical analysis of stock trends. CRC Press, Boca Raton (2007)
Bulkowski, T.N.: Encyclopedia of chart patterns. Wiley, New York (2011)
Neri, F.: Learning and predicting financial time series by combining natural computation and agent simulation. In: Chio, C., et al. (eds.) EvoApplications 2011, Part II. LNCS, vol. 6625, pp. 111–119. Springer, Heidelberg (2011)
Otero, F.E.B., Kampouridis, M.: A comparative study on the use of classification algorithms in financial forecasting. In: Esparcia-Alcázar, A.I., Mora, A.M. (eds.) EvoApplications 2014. LNCS, vol. 8602, pp. 276–287. Springer, Heidelberg (2014)
Lohpetch, D., Corne, D.: Outperforming buy-and-hold with evolved technical trading rules: Daily, weekly and monthly trading. In: Di Chio, C., Brabazon, A., Di Caro, G.A., Ebner, M., Farooq, M., Fink, A., Grahl, J., Greenfield, G., Machado, P., O’Neill, M., Tarantino, E., Urquhart, N. (eds.) EvoApplications 2010, Part II. LNCS, vol. 6025, pp. 171–181. Springer, Heidelberg (2010)
Hochreiter, R.: Evolutionary multi-stage financial scenario tree generation. In: Chio, C., et al. (eds.) EvoApplications 2010, Part II. LNCS, vol. 6025, pp. 182–191. Springer, Heidelberg (2010)
Gabrielsson, P., König, R., Johansson, U.: Evolving hierarchical temporal memory-based trading models. In: Esparcia-Alcázar, A.I. (ed.) EvoApplications 2013. LNCS, vol. 7835, pp. 213–222. Springer, Heidelberg (2013)
Loginov, A., Heywood, M.I.: On the utility of trading criteria based retraining in forex markets. In: Esparcia-Alcázar, A.I. (ed.) EvoApplications 2013. LNCS, vol. 7835, pp. 192–202. Springer, Heidelberg (2013)
Vassiliadis, V., Thomaidis, N., Dounias, G.: On the performance and convergence properties of hybrid intelligent schemes: Application on portfolio optimization domain. In: Chio, C., et al. (eds.) EvoApplications 2011, Part II. LNCS, vol. 6625, pp. 131–140. Springer, Heidelberg (2011)
Michalak, K.: Selecting best investment opportunities from stock portfolios optimized by a multiobjective evolutionary algorithm. In: Proceedings of the 2015 on Genetic and Evolutionary Computation Conference, pp. 1239–1246. ACM (2015)
Beasley, J.E., Meade, N., Chang, T.J.: An evolutionary heuristic for the index tracking problem. Eur. J. Oper. Res. 148(3), 621–643 (2003)
Høyland, K., Wallace, S.W.: Generating scenario trees for multistage decision problems. Manage. Sci. 47(2), 295–307 (2001)
Michalak, K., Filipiak, P., Lipinski, P.: Usage patterns of trading rules in stock market trading strategies optimized with evolutionary methods. In: Esparcia-Alcázar, A.I. (ed.) EvoApplications 2013. LNCS, vol. 7835, pp. 234–243. Springer, Heidelberg (2013)
Haykin, S., Lippmann, R.: Neural networks, a comprehensive foundation. Int. J. Neural Syst. 5(4), 363–364 (1994)
Devadoss, A.V., Ligori, T.A.A.: Forecasting of stock prices using multi layer perceptron. Int. J. Comput. Algorithm 2, 440–449 (2013)
Hagan, M.T., Demuth, H.B., Beale, M.H., et al.: Neural network design. Pws Pub, Boston (1996)
Arthur, D., Vassilvitskii, S.: k-means++: The advantages of careful seeding. In: Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms, Society for Industrial and Applied Mathematics, pp. 1027–1035 (2007)
Nguyen, D., Widrow, B.: Improving the learning speed of 2-layer neural networks by choosing. In: Initial Values of the Adaptive Weights, International Joint Conference of Neural Networks, pp. 21–26 (1990)
Fu, T.C., Chung, F.l., Ng, V., Luk, R.: Pattern discovery from stock time series using self-organizing maps, Citeseer
Srikant, R., Vu, Q., Agrawal, R.: Mining association rules with item constraints. KDD 97, 67–73 (1997)
Ye, Y., Chiang, C.C.: A parallel apriori algorithm for frequent itemsets mining. In: Fourth International Conference on Software Engineering Research, Management and Applications, 2006, IEEE, pp. 87–94 (2006)
Borgelt, C., Kruse, R.: Induction of association rules: Apriori implementation. In: Compstat, Physica-Verlag HD, pp. 395–400 (2002)
Chang, T.J., Meade, N., Beasley, J.E., Sharaiha, Y.M.: Heuristics for cardinality constrained portfolio optimisation. Comput. Oper. Res. 27(13), 1271–1302 (2000)
Anagnostopoulos, K., Mamanis, G.: A portfolio optimization model with three objectives and discrete variables. Comput. Oper. Res. 37(7), 1285–1297 (2010)
Branke, J., Scheckenbach, B., Stein, M., Deb, K., Schmeck, H.: Portfolio optimization with an envelope-based multi-objective evolutionary algorithm. Eur. J. Oper. Res. 199(3), 684–693 (2009)
Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: Nsga-ii. IEEE Trans. Evol. Comput. 6(2), 182–197 (2002)
Anagnostopoulos, K., Mamanis, G.: The mean-variance cardinality constrained portfolio optimization problem: An experimental evaluation of five multiobjective evolutionary algorithms. Expert Syst. Appl. 38(11), 14208–14217 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Deplano, I., Squillero, G., Tonda, A. (2016). Portfolio Optimization, a Decision-Support Methodology for Small Budgets. In: Squillero, G., Burelli, P. (eds) Applications of Evolutionary Computation. EvoApplications 2016. Lecture Notes in Computer Science(), vol 9597. Springer, Cham. https://doi.org/10.1007/978-3-319-31204-0_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-31204-0_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-31203-3
Online ISBN: 978-3-319-31204-0
eBook Packages: Computer ScienceComputer Science (R0)