Credibility Mean-Semi-Entropy-Skewness-Kurtosis Multi-Stage Portfolio Selection Model

In this paper, the problem of asset diversification portfolio selection is discussed under fuzzy uncertainty. Firstly, a multi-stage portfolio selection model of credibility means half-entropy-skewness-kurtosis is built, in which the real constraints are considered such as wealth balance constraints, cardinality constraints, upper and lower limit constraints, budget constraints, and not allowing short-selling; Meanwhile, triangular fuzzy variables are used to represent asset returns, skewness and kurtosis; credibility semi-entropy is used to quantify investment risks; the portfolio mean and skewness are maximized; half-entropy and kurtosis are minimized in the proposed model. Secondly, a multi-objective firefly-symbiont search algorithm is designed to solve the model. Finally, the validity of the proposed model and algorithm is verified by selecting the historical transaction data of 12 Shanghai Stock Exchanges for empirical analysis.