Portfolio optimization with mean absolute deviation model using particle swarm optimization algorithm: A case study in Indonesia during Covid-19 pandemic

Abstract

Many companies listed on the Indonesia Stock Exchange (IDX) are worried about the policies issued by the government as a result of the pandemic which may later affect the market response and stock price movements. The purpose of this research is to minimize the risks and maximize return on stock investments in the form mean absolute deviation (MAD) model and apply the particle swarm optimization (PSO) algorithm based on historical data to obtain optimal solution. The first stage in this research is to model portfolio optimization into the MAD linear programming model followed by solving the model. The development of the PSO algorithm which will be compiled and evaluated based on the fitness value using MATLAB tool. The results of the proportions were compared, and the obtained optimal weight is handed to the selected stocks from the return and portfolio risk. The results showed that the MAD model using PSO algorithms have the consistency and speed of convergent solutions in developing and optimizing stock portfolios and are certainly has better performance than MAD model. The best fitness value is found in optimizing the MAD model portfolio with PSO which is 0.39517 or 39.51%, while the MAD model has a fitness value of 0.39371 or 39.37%.