Abstract
In the financial field, the selection of a Portfolio of assets is a problem faced by individuals and institutions worldwide. Many portfolios at different risk aversion levels have to be considered before taking the decision to buy a specific Portfolio. Throughout this paper we present a reinforcement learning method to select risk aversion levels to populate the portfolio efficient frontier using a weighted sum approach. The proposed method selects an axis of the Pareto front and calculates the next risk aversion value to fill the biggest gap between points located in the efficient frontier. The probability of selecting an axis is updated by a reinforcement learning mechanism each time a non-dominated portfolio is found. By comparing to a strategy which selects risk aversion levels at random, we found that a quick initial efficient frontier is found faster by the proposed methodology. Real world restrictions such as portfolio value and rounded lots are considered to give a realistic approach to the problem.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
de Castro Aranha, C., Iba, H.: A tree-based ga representation for the portfolio optimization problem. In: Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation, GECCO 2008, pp. 873–880. ACM, New York (2008)
de Castro Aranha, C., Iba, H.: Using memetic algorithms to improve portfolio performance in static and dynamic trading scenarios. In: Proceedings of the 11th Annual Conference on Genetic and Evolutionary Computation, GECCO 2009, pp. 1427–1434. ACM, New York (2009)
Arriaga, J., Valenzuela-Rendón, M.: Steepest ascent hill climbing for portfolio selection. In: Di Chio, C., et al. (eds.) EvoApplications 2012. LNCS, vol. 7248, pp. 145–154. Springer, Heidelberg (2012)
Chang, T.J., Meade, N., Beasley, J., Sharaiha, Y.: Heuristics for cardinality constrained portfolio optimisation. Computers and Operations Research 27, 1271–1302 (2000)
Chiam, S., Al Mamun, A., Low, Y.: A realistic approach to evolutionary multiobjective portfolio optimization. In: IEEE Congress on Evolutionary Computation, CEC 2007, pp. 204–211 (September 2007)
Gao, J., Chu, Z.: An improved particle swarm optimization for the constrained portfolio selection problem. In: International Conference on Computational Intelligence and Natural Computing, CINC 2009, vol. 1, pp. 518–522 (June 2009)
Hassan, G., Clack, C.D.: Multiobjective robustness for portfolio optimization in volatile environments. In: Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation, GECCO 2008, pp. 1507–1514. ACM, New York (2008)
Lu, J., Liechty, M.: An empirical comparison between nonlinear programming optimization and simulated annealing (sa) algorithm under a higher moments bayesian portfolio selection framework. In: 2007 Winter Simulation Conference, pp. 1021–1027 (December 2007)
Maringer, D.: Heuristic optimization for portfolio management [application notes]. IEEE Computational Intelligence Magazine 3(4), 31–34 (2008)
Maringer, D.: Portfolio management with heuristic optimization. Advances in computational management science, vol. 8. Springer, Heidelberg (2005)
Maringer, D., Kellerer, H.: Optimization of cardinality constrained portfolios with a hybrid local search algorithm. OR Spectrum 25, 481–495 (2003), doi:10.1007/s00291-003-0139-1
Maringer, D., Parpas, P.: Global optimization of higher order moments in portfolio selection. Journal of Global Optimization 43, 219–230 (2009), doi:10.1007/s10898-007-9224-3
Maringer, D.G.: Distribution assumptions and risk constraints in portfolio optimization. Computational Management Science 2, 139–153 (2005), doi:10.1007/s10287-004-0031-8
Ponsich, A., Jaimes, A., Coello, C.: A survey on multiobjective evolutionary algorithms for the solution of the portfolio optimization problem and other finance and economics applications. IEEE Transactions on Evolutionary Computation 17(3), 321–344 (2013)
Ryu, J.H., Kim, S., Wan, H.: Pareto front approximation with adaptive weighted sum method in multiobjective simulation optimization. In: Winter Simulation Conference, WSC 2009, pp. 623–633. Winter Simulation Conference (2009)
Winker, P., Maringer, D.: The hidden risks of optimizing bond portfolios under var. Journal of Risk 9(4), 1–19 (2007)
Woodside-Oriakhi, M., Lucas, C., Beasley, J.: Heuristic algorithms for the cardinality constrained efficient frontier. European Journal of Operational Research 213(3), 538–550
Xu, F., Chen, W.: Stochastic portfolio selection based on velocity limited particle swarm optimization. In: The Sixth World Congress on Intelligent Control and Automation, WCICA 2006, vol. 1, pp. 3599–3603 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Arriaga-González, J., Valenzuela-Rendón, M. (2013). Reinforcement Learning Method for Portfolio Optimal Frontier Search. In: Castro, F., Gelbukh, A., González, M. (eds) Advances in Soft Computing and Its Applications. MICAI 2013. Lecture Notes in Computer Science(), vol 8266. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-45111-9_22
Download citation
DOI: https://doi.org/10.1007/978-3-642-45111-9_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-45110-2
Online ISBN: 978-3-642-45111-9
eBook Packages: Computer ScienceComputer Science (R0)