Using memetic algorithms to improve portfolio performance in static and dynamic trading scenarios

ABSTRACT

The Portfolio Optimization problem consists of the selection of a group of assets to a long-term fund in order to minimize the risk and maximize the return of the investment. This is a multi-objective (risk, return) resource allocation problem, where the aim is to correctly assign weights to the set of available assets, which determines the amount of capital to be invested in each asset.

In this work, we introduce a Memetic Algorithm for portfolio optimization. Our system is based on a tree-structured genome representation which selects assets from the market and establish relationships between them, and a local hill climbing function which uses the information available from the tree-structure to calculate the weights of the selected assets.

We use simulations based on historical data to test our system and compare it to previous approaches. In these experiments, our system shows that it is able to adapt to aggressive changes in the market, like the crash of 2008, with reduced trading cost.

REFERENCES

• 1: C. Aranha and H. Iba. Modelling cost into a genetic algorithm-based portfolio optimization system by seeding and objective sharing. In Proc. of the Conference on Evolutionary Computation, pages 196--203, 2007.
• 2: Claus C. Aranha , Hitoshi Iba, A tree-based GA representation for the portfolio optimization problem, Proceedings of the 10th annual conference on Genetic and evolutionary computation, July 12-16, 2008, Atlanta, GA, USA [doi>10.1145/1389095.1389267]
• 3: William Eugene Hart, Adaptive global optimization with local search, University of California at San Diego, La Jolla, CA, 1994
• 4: Ronald Hochreiter, An Evolutionary Computation Approach to Scenario-Based Risk-Return Portfolio Optimization for General Risk Measures, Proceedings of the 2007 EvoWorkshops 2007 on EvoCoMnet, EvoFIN, EvoIASP,EvoINTERACTION, EvoMUSART, EvoSTOC and EvoTransLog: Applications of Evolutionary Computing, April 11-13, 2007, Valencia, Spain [doi>10.1007/978-3-540-71805-5_22]
• 5: Toshihide Ibaraki , Naoki Katoh, Resource allocation problems: algorithmic approaches, MIT Press, Cambridge, MA, 1988
• 6: R. Jiang and K.Y. Szeto. Discovering investment strategies in portfolio management: A genetic algorithm approach. In Proceedings of the 9th International Conference on Neural Information Processing, volume 3, pages 1206--1210, 2002.
• 7: C.-M. Lin and M. Gen. An effective decision-based genetic algorithm approach to multiobjective portfolio optimization problem. Applied Mathematical Sciences, 1(5):201--210, 2007.
• 8: Piotr Lipinski , Katarzyna Winczura , Joanna Wojcik, Building Risk-Optimal Portfolio Using Evolutionary Strategies, Proceedings of the 2007 EvoWorkshops 2007 on EvoCoMnet, EvoFIN, EvoIASP,EvoINTERACTION, EvoMUSART, EvoSTOC and EvoTransLog: Applications of Evolutionary Computing, April 11-13, 2007, Valencia, Spain [doi>10.1007/978-3-540-71805-5_23]
• 9: H. Markowitz. Mean-Variance analysis in Portfolio Choice and Capital Market. Basil Blackwell, New York, 1987.
• 10: S. ping Chen, C. Li, S.-H. Li, and X. wei Wu. Portfolio optimization with transaction costs. Acta Mathematicae Applicatae Sinica, 18(2):231--248, 2002.
• 11: F. Streichert, H. Ulmer, and A. Zell. Evolutionary algorithms and the cardinality constrained portfolio optimization problem. In D. Ahr, R. Fahrion, M. Oswald, and G. Reinelt, editors, Operations Research Proceedings. Springer, September 2003.
• 12: Harish Subramanian , Subramanian Ramamoorthy , Peter Stone , Benjamin J. Kuipers, Designing safe, profitable automated stock trading agents using evolutionary algorithms, Proceedings of the 8th annual conference on Genetic and evolutionary computation, July 08-12, 2006, Seattle, Washington, USA [doi>10.1145/1143997.1144285]
• 13: B. Ullah, R. Sarker, D. Cornforth, and C. Lokan. An agent-based memetic algorithm (ama) for solving constrained optimization problems. In IEEE Congress on Evolutionary Computation (CEC), pages 999--1006, Singapore, September 2007.
• 14: Wei Yan , Christopher D. Clack, Behavioural GP diversity for dynamic environments: an application in hedge fund investment, Proceedings of the 8th annual conference on Genetic and evolutionary computation, July 08-12, 2006, Seattle, Washington, USA [doi>10.1145/1143997.1144290]
• 15: Wei Yan , Christopher D. Clack, Evolving robust GP solutions for hedge fund stock selection in emerging markets, Proceedings of the 9th annual conference on Genetic and evolutionary computation, July 07-11, 2007, London, England [doi>10.1145/1276958.1277384]
• 16: Yuh-Dauh-Lyu. Financial Engineering and Computation. Cambridge Press, 2002.

INDEX TERMS

Primary Classification:
  J. Computer Applications
  J.1 ADMINISTRATIVE DATA PROCESSING
      Subjects: Financial (e.g., EFTS)

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.8 Problem Solving, Control Methods, and Search
          Subjects: Heuristic methods

General Terms:
Algorithms, Experimentation

Keywords:
memetic algorithm, operational research, portfolio