Algorithm based on heuristic subspace searching strategy for solving investment portfolio optimization problems

There exist many difficulties when investment portfolio problems based on Markowitz model are solved by using some traditional methods, such as Newton method, conjugate gradient method, etc. One of the difficulties is that Markowitz model has rigorous constraint conditions. Evolutionary computation is a parallel global optimization algorithm with high efficiency and it has been widely used in portfolio investment field. A heuristic subspace searching algorithm is put forward in this paper for solving investment portfolio optimization problems based on Markowitz model. The experimental results indicate that this algorithm has an improved efficiency compared with traditional evolutionary computation.