Prospect Theory-Based Formulation of Portfolio Optimization Problem using Loan And Its Solution by Evolutionary Algorithm

Portfolio optimization that allows the borrowed money from a loan to be invested in risk assets is formulated as a data-driven optimization problem called POL_P. Then, in order to reflect investor preferences called “values” in the solution, or the portfolio, prospect theory is used to extend POL_P to another optimization problem called POL_ V. POL_P maximizes the profit of the portfolio, while POL_ V maximizes the value of the portfolio. An evolutionary algorithm with a novel constraint-handling technique is proposed for solving POL_P and POL_ V. Finally, the solutions to POL_P and POL_ V are compared and discussed through experiments using historical asset data.