One of the most studied problems in the financial is the intractability of the portfolios. Some practical formulations of the problem include various kinds of nonlinear constraints and objectives and can be efficiently solved by approximate algorithms. In this paper, we present a meta-heuristic algorithm named Particle Swarm Optimization (PSO) to the construction of optimal risky portfolios for financial investments. The PSO algorithm is tested on two portfolio optimization models and a comparative study with Genetic Algorithm has been implemented. The PSO model demonstrates high computational efficiency in constructing optimal risky portfolios. Preliminary results show that the approach is very promising and achieves results comparable or superior with the state of the art solvers.