Multiperiod Portfolio Performance Evaluation Model Based on Possibility Theory

This article discusses a multiperiod fuzzy portfolio optimization problem with some realistic constraints, in which the returns of risky assets are characterized by fuzzy variables. First, we extend the possibilistic mean value of a normal fuzzy number to a generalized case, and define two performance evaluation indicators to measure the effects of the negative and the positive volatilities on portfolio selection. Second, we propose a multiperiod portfolio performance evaluation model under the realistic assumptions of return demand, risk control, cardinality constraint, and round lots constraint. Then, we design a novel feasibility-based particle swarm optimization (NFBPSO) algorithm to solve the proposed model. Finally, we provide a numerical example to illustrate the idea of our model and demonstrate the effectiveness of the designed algorithm.