E. Almaraz Luengo, E. Almaraz Luengo, M. Luengo y Dos Santos
It is studied extensions of the classical Markowitz's portfolio selection model in a fuzzy context using new fuzzy measures. Markowitz's M-V model presents the investor's problem as a mathematical programming problem. Fuzzy theory allows us to represent the investor's preferences. It is possible to integrate these techniques and to consider portfolio selection problems in fuzzy contexts. Though variance (v) has been a popular risk measure, it considers that deviations above the mean (m) are equally undesirable than deviations below m, but in economic context, since low part deviation from m means possible loss of wealth and high part deviation from m means the existence of potential return, it has shown that semivariance is better, as a risk measure, than v. Due to this fact, a new approximation is proposed, introducing the crisp possibilistic semivariance of a fuzzy number and defining the optimization problems for that risk measure. Some numerical examples are given.
Palabras clave: fuzzy number, mean-variance model, mean-semivariance model, portfolio selection
Programado
XC1a Pósters (Estadística)
18 de abril de 2012 12:00
Salón Madrid
