A copula-based scenario tree generation algorithm for multiperiod portfolio selection problems (Q827151)

The authors consider a multiperiod portfolio selection problem for a global equity investor based on an underlying return model with a stochastic volatility process and a dynamic copula function to capture markets' co-movements. The problem is formulated as a discrete multistage stochastic program (MSP). A scenario generation algorithm able to capture time-varying asymmetric tail dependence, and evaluate resulting optimal investment policies is proposed. The scenario tree aims at approximating a stochastic process combining an ARMA-GARCH model and a dynamic Student-t-Clayton copula. A set of empirical results is presented to validate the adopted statistical approach and the optimal portfolio strategies.