International Journal of
Physical Sciences

  • Abbreviation: Int. J. Phys. Sci.
  • Language: English
  • ISSN: 1992-1950
  • DOI: 10.5897/IJPS
  • Start Year: 2006
  • Published Articles: 2569

Full Length Research Paper

An evolutionary multi-objective optimization algorithm for portfolio selection problem

  Guillermo Cabrera G.1*, Claudia Vasconcellos1, Ricardo Soto1,2, Jose Miguel Rubio3, Fernando Paredes4 and Broderick Crawford1,5      
1Escuela de Ingeniería Informatica, Pontificia Universidad Católica de Valparaíso, Chile. 2Universidad Autónoma de Chile, Chile. 3Universidad de Playa Ancha, Chile. 4Escuela de Ingeniería Industrial, Universidad Diego Portales, Santiago, Chile. 5Universidad Técnica Federico Santa María, Chile.
Email: [email protected].

  •  Accepted: 29 July 2011
  •  Published: 02 October 2011


Cultural algorithms (CAs) are one of the metaheuristics which can be adapted in order to work in multi-objective optimization environments. On the other hand, portfolio selection problem (PSP) is a well-know problem in literature. However, only a few articles have applied evolutionary multi-objective (EMO) algorithms to these problems and articles presenting CAs applied to the PSP have not been found. In this article, we present a bi-objective cultural algorithm (BOCA) which has been applied to the PSP, and obtaining acceptable results in comparison with other well-known EMO algorithms from the literature. The considered criteria of the problem are risk minimization and profit maximization. The different solutions obtained with the BOCA have been compared using max-delta-area metric.


Key words: Constraint programming, autonomous search, heuristic search.


 CAs, Cultural algorithms; PSP, portfolio selection problem; EMO,evolutionary multi-objective; BOCA, bi-objective cultural algorithm; EVL, extended virtual loser; PF, Pareto frontier; MOEA, multi-objective evolutionary algorithms.