Optimizing portfolio risk control based on the particle swarm algorithm in the stock exchange

Document Type : Original Article

Authors
nasim mohammadhasani 1
narges yazdanian 2
Jafar Jamali 3
maryam teimourian 4
1 PhD student in Financial Engineering, Department of Financial Management, Faculty of Management and Economics, Roudhan Branch, Islamic Azad University, Tehran, Iran.
2 Assistant Professor, Department of Financial Management, Department of Financial Management, Faculty of Management and Economics, Roudhan Branch, Islamic Azad University, Tehran, Iran.
3 Assistant Professor, Department of Financial Management, Faculty of Management and Economics, Science and Research Unit, Islamic Azad University, Tehran, Iran.
4 Assistant Professor, Department of Statistics and Mathematics, Rodhan Branch, Islamic Azad University, Tehran, Iran.
10.30495/jik.2025.23838
Abstract
Optimizing the investment portfolio is a challenging issue in financial fields. Several methods have been presented with the aim of minimizing risk and maximizing capital return to form an optimal investment portfolio. In this research, the improved particle swarm algorithm has been used to optimize risk control in the portfolio. In this research, the data of the second quarter of 1402 has been used for 50 active companies of Tehran Stock Exchange. The improved pso has reached convergence at the 84th stage and the result of selecting companies for investment with lower risk is 23 companies out of the 50 mentioned companies. Sharp's share return ratio is equal to 17.69 for 23 selected companies, while it is equal to 11.56 for all companies, indicating a reduction in investment risk and an increase in profit in the selected companies.The high level of this criterion represents the yield achieved with less risk. Also, Trainor's measure for share return is 0.15 for 23 selected companies and 0.12 for 50 active companies, the value of this measure for 23 selected companies is slightly higher than for 50 active companies. Trainer is the relationship between portfolio return and market rate of return. The higher the amount of trainer, the better portfolio is created. Jensen's measure of return on equity is the same for 23 selected companies and 50 active companies and is equal to 0.22. According to the research results, the value of all three performance evaluation criteria of Sharp, Trainor and Jensen for EPS of each share in selected companies is better than 50 companies
راموز، نجمه، اکبری آق مشهدی، زهرا، عاطفت دوست، علیرضا، (1399)، انتخاب پرتفوی بهینه با استفاده از مدل برنامه ریزی توافقی در بورس اوراق بهادار تهران، راهبرد مدیریت مالی، 21-37.
شیوعی، کامیار، شیوعی، پویا، (1395)، مدل سازی پیش بینی شاخص بازار بورس تهران با استفاده از الگوریتم ازدحام ذرات، دومین کنفرانس بین المللی حسابداری، اقتصاد و مدیریت مالی.
صیادی، مهدی، بیگ زاده عباسی، فرزانه، درخشان داوری، مژگان، (1394)، مطالعه تطبیقی برای انتخاب پرتفولیوی بهینه با اهداف غیرخطی با استفاده از الگوریتم های ژنتیک و ازدحام ذرات در بورس اوراق بهادار تهران. اولین کنفرانس بین المللی مدیریت، اقتصاد، حسابداری و علوم تربیتی.
نیکزاد، رضا،  نیکزاد، رویا ، (1396) ، مقایسه الگوریتم های بهینه یابی در بهینه سازی پرتفوی سهام، همایش بین المللی مدیریت، اقتصاد و بازاریابی، تهران، مرکز همایش های کوشا گستر.
Chen, B. Zeng, W. Lin, Y. Zhang, D., A new local search-based multiobjective optimization algorithm, IEEE Trans. Evol. Comput. 19 (1) (2015) 50–73.
Chen, Z.GZhan, . Z.H. Lin, Y. Gong, Y.J. Gu, T.L. Zhao, F. Yuan, H.Q. Chen, X.F. Li, Q. Zhang, J. Multiobjective cloud workflow scheduling: A multiple populations ant colony system approach, IEEE Trans. Cybern. 49 (8) (2019) 2912–2926.
Dai, Z., & Wang, F. (2019). Sparse and robust mean–variance portfolio optimization problems. Physica A: Statistical Mechanics and its Applications, 523, 1371-1378.
Yao, G. Ding, Y. Jin, Y. Hao, K. Endocrine-based coevolutionary multi-swarm for multi-objective workflow scheduling in a cloud system, Soft Comput. 21 (15) (2017) 4309–4322.
Gavrishchaka, V.V., Ganguli, S.B. Volatility forecasting from multiscale and high-dimensional market data, Neurocomputing 55 (1-2) (2003) 285–305.
Gu, Q., & Hao, X. (2018). Adaptive iterative learning control based on particle swarm optimization. The Journal of Supercomputing, 76(5), 3615-3622.
 Liang, X, Chen, R.C. He, Y.B. Chen, Y. Associating stock prices with web financial information time series based on support vector regression, Neurocomputing 115 (2013) 142–149.
Relich, M, P. Pawlewski, A fuzzy weighted average approach for selecting portfolio of new product development projects, Neurocomputing 231 (2017)
Song, Q, A. Liu, S.Y. Yang, Stock portfolio selection using learning-to-rank algorithms with news sentiment, Neurocomputing 264 (2017) 20–28.
Tang, Q., Li, Y., Deng, Z., Chen, D., Guo, R., & Huang, H. (2019). Optimal shape design of an autonomous underwater vehicle based on multi-objective particle swarm optimization. Natural Computing, 19(4), 733-742.
Tian, Y. Zhang, T. Xiao, J. Zhang, X. Jin, Y. A coevolutionary framework for constrained multi-objective optimization problems, IEEE Trans. Evol. Comput., DOI: 10.1109/TEVC.2020.3004012.
Van Staden, P. M., Dang, D. M., & Forsyth, P. A. (2020). The surprising robustness of dynamic Mean-Variance portfolio optimization to model misspecification errors. European Journal of Operational Research.
Wang, S., Yu, C., Shi, D., & Sun, X. (2018). Research on speed optimization strategy of hybrid electric vehicle queue based on particle swarm optimization. Mathematical Problems in Engineering, 2018.
Xu, L., Yang, W., & Tian, H. (2019). Correction to: Design of Wideband CIC Compensator Based on Particle Swarm Optimization. Circuits, Systems, and Signal Processing, 38(6), 2890-2891.