Optimal Portfolio Choice under Hidden Regime Switching Model

We investigate a portfolio optimization problem in a continuous-time Markov-modulated financial market. The unobservable mean return of a risky asset follows a continuous-time, two-state Markov chain whose states are interpreted as different states of market. Using results from filter theory, we reduce this problem to one with complete observation. We solve the problem by stochastic control methods and the optimal portfolio can be explicitly characterized by stochastic integrals. The Monte Carlo simulations are implemented to compute the optimal portfolio allocations. The results show that state uncertainty have a great influence on optimal portfolio choice. The parameter uncertainty prompts the investor to hedge against unanticipated changes in the state variables.