PORTFOLIO SELECTION BASED ON A NONLINEAR NEURAL NETWORK: AN APPLICATION ON THE ISTANBUL STOCK EXCHANGE (ISE30)

Abstract

Portfolio optimization is frequently used method for the best portfolio selection, according to some ob jective. Heuristic techniques designed forsolving a problem Önding an approximate solution when classic methods fail toÖnd any exact solution, have often used in portfolio selection problem. However, almost none of these techniques used a neural network to allocate the proportion of stocks. The main goal of portfolio optimization problem is minimizing the risk of portfolio while maximizing the expected return of the portfolio.This study tackles a neural network in order to solve the portfolio optimizationproblem. The data set is the daily price of Istanbul Stock Exchange-30 (ISE30) from May 2015 to May 2017. This study uses Markowitzís Mean-Variancemodel. Indeed, the portfolio optimization model is quadratic programming(QP) problem. Therefore, many heuristic methods were used to solve portfolio optimization method such as particle swarm optimization, ant colonyoptimization etc. In fact, these methods do not satisfy stock markets demandsin the Önancial world. This study proposed a nonlinear neural network tosolve the portfolio optimization problem. In the implementation phase, theproposed method for portfolio optimization problem has more e§ective resultsthan present methods.