Ant Colony Optimization Based Portfolio Selection According to Yield-Risk Ratio: An Example of Bist-30
DOI:
https://doi.org/10.20491/isarder.2022.1468Keywords:
Work Meaning, Work Performance, Education ManagersAbstract
Purpose – The main purpose of the study is to select the best portfolio according to the determined criteria by examining the sales of BIST-30 companies traded in the stock exchange between September 2019 and August 2021. Design/methodology/approach – The data obtained from Bist-30 companies were transferred to the MATLAP platform and analyzed with the Ant Colony Algorithm developed and the optimum portfolio was tried to be calculated. The data of the companies were taken from Borsa İstanbul and the companies were numbered from 1 to 30. The system was run according to the risk values determined by the users and optimum portfolios were determined. Results – The risk coefficient taken in the study is shown with Ϭ (Sigma). As a result of the study, it is expected that the selected portfolio will be 14 in cases where Ϭ=0.20. It is seen that as the risk coefficient increases, the portfolio selection that should be selected increases. This fact shows that the performance of the developed algorithm decreases as the risk coefficient increases. According to these results, significant changes were experienced for portfolio selection with the ant colony algorithm and changes were observed in the risk and yield curves depending on these changes. Discussion – Considering the results obtained in the selection of the Ant Colony Algorithm-based portfolio carried out within the scope of the study, it has been observed that it gives very productive results, especially in cases where Ϭ=0.20. In addition, the performance of this algorithm was evaluated at 6 different coefficients for the selection of risk and return values left to the users.
Downloads
Published
How to Cite
Issue
Section
License
![Creative Commons License](http://i.creativecommons.org/l/by-nd/4.0/88x31.png)
This work is licensed under a Creative Commons Attribution-NoDerivatives 4.0 International License.