teaching-learning-based optimization (tlbo) algorithm

Increasing the profits and reducing the risks have always been of the most important issues of concern to the investors in the financial markets. In recent years, many solutions and proposals have been suggested in respect to the frequency of portfolio optimization issue, with the highest return and the lowest possible risk. One of the most prominent suggestions is the Markowitz Model which is mostly known as the Modern Portfolio Theory. On the other hand, the TLBO algorithm which has been presented in 2010 is one of the most efficient meta-heuristic methods to solve the optimization problem. In this study, we are attempting to solve the portfolio optimization problem, according to the framework of the model introduced by Markowitz and using TLBO algorithm. For this purpose, the data related to the returns of 20 companies listed in TSE during the period 2012-2016 were collected. It is worth mentioning that four criteria including variance, mean absolute deviation, semi-variance and conditional value at risk (CvaR) were used in order to measure the risk level in this investigation.