6533b7d1fe1ef96bd125c137

RESEARCH PRODUCT

A multi-objective genetic algorithm for cardinality constrained fuzzy portfolio selection

Enriqueta VercherJosé D. BermúdezJosé Vicente Segura

subject

Mathematical optimizationCardinalityComputer Science::Computational Engineering Finance and ScienceArtificial IntelligenceLogicDownside riskPortfolioFuzzy set operationsFuzzy numberPost-modern portfolio theoryPortfolio optimizationFuzzy logicMathematics

description

This paper presents a new procedure that extends genetic algorithms from their traditional domain of optimization to fuzzy ranking strategy for selecting efficient portfolios of restricted cardinality. The uncertainty of the returns on a given portfolio is modeled using fuzzy quantities and a downside risk function is used to describe the investor's aversion to risk. The fitness functions are based both on the value and the ambiguity of the trapezoidal fuzzy number which represents the uncertainty on the return. The soft-computing approach allows us to consider uncertainty and vagueness in databases and also to incorporate subjective characteristics into the portfolio selection problem. We use a data set from the Spanish stock market to illustrate the performance of our approach to the portfolio selection problem.

yearjournalcountryeditionlanguage
2012-02-01Fuzzy Sets and Systems
https://doi.org/10.1016/j.fss.2011.05.013