Portfolio selection problem was first formulated in a paper written by Markowitz, where investment diversification can be translated into computing. Mean-variance model he introduced has been used and developed because of it's limitations in the larger constraints found in the real world, as well as it'scomputational complexity which found when it used in large-scale portfolio. Quadratic programming model complexity given by Markowitz has been overcome with the development of the algorithm research. Theyintroduce a linear risk function which solve the portfolio selection problem with real constraints, i.e. minimum transaction lots. With the Mixed Integer Linear models, proposed a new heuristic algorithm that starts from the solution of the relaxation problems which allow finding close-to-optimal solutions. This algorithm is built on Mixed Integer Linear Programming (MILP) which formulated using nearest integer search method.