포트폴리오 결정에 관한 연구 The problem of selecting a portfolio is to find an investment plan that achieves a desired return while minimizing the risk involved. One stream of algorithms is based upon the mixed integer linear programming(ILP) models that are based upon the Markowitz model. These algorithms can generate optimal solutions but require too much time to apply to real problems. As an alternative approach, several heuristic algorithms are introduced by many authors. In this paper, we introduce an algorithm for the ILP portfolio problems. The proposed algorithm is tested using Korean stock market data to verify its accuracy and efficiency. We find that our algorithm can generate solutions of good quality in a considerably short time.