Applying Genetic Optimization Algorithm in Selecting Portfolios of listed companies at Tehran Stock Exchange
Selecting a portfolio is one of the most critical issues in investment. In this process, the investor faces numerous alternatives and he must choose the most optimized one. Determining which shares are most suitable to be put in the portfolio and capital allocation between them, are complex issues....
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | fas |
| Published: |
Shahid Bahonar University of Kerman
2008-06-01
|
| Series: | مجله توسعه و سرمایه |
| Online Access: | https://jdc.uk.ac.ir/article_1887_eaadbf2a1e6af06435061a57aecdf7d7.pdf |
| Summary: | Selecting a portfolio is one of the most critical issues in investment. In this process, the investor faces numerous alternatives and he must choose the most optimized one. Determining which shares are most suitable to be put in the portfolio and capital allocation between them, are complex issues. Theoretically, assuming constant return, we can minimize the risk by applying a quadratic equation, but experimentally and with respect to the Diverse investing tools and different investor's utility functions, the mathematical approach for solving this model requires vast calculation and planning. The main object of this research is applying genetic optimization algorithm in selecting a portfolio from Tehran Stock Exchange, listed companies, In away that the chosen portfolio minimize the investment risk while maximizing the return. In order to do this, we choose 40 companies shares from the population. After calculating the main variables – monthly risk and return for an eight year period- and preparing the required algorithm, the results are compared with Markowitz and the Random choice models ones in different levels of portfolio and with respect to hypotheses. Relevant statistical tests on 1st and 2nd hypotheses showed a meaningful difference; furthermore the genetic algorithm results defeated the Markowitz and the Random choice models. |
|---|---|
| ISSN: | 2008-2428 2645-3606 |