Systematic Initialization Approaches for Portfolio Optimization Problems

Selecting the number of assents to obtain the maximized expected return under the possible lowest risk is the main concern of portfolio optimization problems. Optimization algorithms -multi/many-objective- are evaluated to find the desired/possible level of investment. Converging to the best possible asset set and -if possible- distribution of the many possible solution sets for an efficient frontier is expected as the result of the multi/many-objective optimization algorithms. Obtaining an accurate and well-distributed set of solutions is the main motivation. Hence, in this paper, two initialization approaches are proposed for multi/many-objective optimization algorithms to obtain a better convergence and distribution solution set for the portfolio optimization problem. The initial population set is composed of the assets with the largest income and binary combinations of the assets where their sum returns the maximum income. These proposed approaches are integrated with eight different optimization algorithms and the performance of the algorithms is compared with respect to the convergence and diversity metrics.