Swarm intelligent optimisation based stochastic programming model for dynamic asset allocation

Asset allocation is critical for the portfolio management process. In this paper, we solve a dynamic asset allocation problem through a multiperiod stochastic programming model. The objective is to maximise the expected utility of wealth at the end of the planning periods. To improve the optimisation result of the model, we employ swarm intelligent optimisers, the Bacterial Foraging Optimisation (BFO) algorithm and the Particle Swarm Optimisation (PSO) algorithm. A hybrid optimiser using the Bacterial Foraging Optimisation algorithm for initialisation and the Sequential Quadratic Programming (SQP) for local search is also suggested. The results are compared with the standard-alone SQP and the canonical Genetic Algorithm. The numerical results suggest the hybrid method provides better result, with improved accuracy, stability and computing speed than using BFO, PSO, GA, or SQP alone.