Intelligent method for dynamic portfolio selection with probability criterion

The intelligent method for solving the problem of dynamic portfolio selection with probability criterion is investigated in this paper. The criterion function is the sum of probability that the return rate of portfolio at the end of each period is not less than a given expected rate or the probability that the terminal return rate of portfolio is no less than a given expected rate. Since the criterion function cannot be calculated by analytic formulation, the traditional methods for solving it are no longer valid. The purpose of this paper, therefore, is to focus on the design of a new method for the problem of dynamic portfolio selection with probability criterion. The stochastic simulation based genetic algorithm and artificial neural network are embedded within dynamic programming, and the intelligent method for solving the optimal problem is given. Two examples show that this intelligent method is efficient.