Application of artificial intelligence algorithms in stock market forecasting

Document Type : Research Paper

Authors

1 Department of Accounting, Tabriz Branch, Islamic Azad University, Tabriz, Iran

2 Department of Economic, Tabriz Branch, Islamic Azad University, Tabriz, Iran

Abstract

New methods of machine learning in Artificial Intelligence (AI), changing the parameters and naturally finding the most logical and optimal solution possible based on what has been learned in the past, reducing the search space, reduce decision error. The use of these new methods of calculation, mathematics, and artificial intelligence has increased in recent years in the capital market, but most of the methods of portfolio construction are based on the traditional methods of the past and, of course, more in the category of asset classification. In this paper, most algorithms that had been used in other research are implemented and tested. The results of this research show that PSO (Particle Swarm Optimization) and GWO (Grey Wolf Optimizer) are the best algorithms for forecasting financial markets. Both algorithms have the same capability and show good results.

Keywords

[1] V. Agarwal, C.C. James, C.E. Widdicombe and A.D. Barton, Intraseasonal predictability of natural phytoplankton population dynamics, Eco. Evol. 11 (2021), no. 22, 15720–15739.

[2] E. Atashpaz-Gargari and C. Lucas, Imperialist competitive algorithm: an algorithm for optimization inspired by imperialistic competition, 2007 IEEE Cong. Evol. Comput., 2007, pp. 4661–4667.
 
[3] A. Chaouki, S. Hardiman, C. Schmidt, E. S´eri´e and J. De Lataillade, Deep deterministic portfolio optimization, J. Finance Data Sci. 6 (2020), 16–30.

[4] M. Corazza, G. di Tollo, G. Fasano, R. Pesenti, A novel hybrid PSO-based metaheuristic for costly portfolio selection problems, Annal. Operat. Res. 304 (2021), no. 1, 109–137.

[5] F.J. Fabozzi, F. Gupta, H.M. Markowitz, The legacy of modern portfolio theory, J. Invest. 11 (2002), no. 3, 7–22.

[6] J. Kennedy, R. Eberhart, Particle swarm optimization, Proc. ICNN’95 Int. Conf. Neural Networks 4 (1995), 1942–1948.

[7] A.T. Khan, X. Cao, S. Li, B. Hu and V.N. Katsikis, Quantum beetle antennae search: a novel technique for the constrained portfolio optimization problem, Sci. China Inf. Sci. 64 (2021), no. 5, 1–4.

[8] D. Kriksciuniene, V. Sakalauskas and A. Imbrazas, Grey wolf optimization model for the best mean-variance based stock portfolio selection, Int. Conf. Innov. Bio-Inspired Comput. Appl. Springer, Cham, 2020, pp. 120–130.

[9] H. Markowitz, Portfolio selection, J. Finance 7 (1952), no. 1, 77–91.

[10] H. Marling and S. Emanuelsson,The Markowitz portfolio theory, http://www.smallake.kr/wpcontent/uploads/2016/04/HannesMarling SaraEmanuelsson MPT.pdf, 25 (2012), 1–6.
 
[11] K. Mazumdar, D. Zhang and Y. Guo, Portfolio selection and unsystematic risk optimisation using swarm intelligence, J. Bank. Financ. Technol. 4 (2020), no. 1, 1–4.

[12] K. Meng, H. Yang, X. Yang and C.K. Wai Yu, Portfolio optimization under a minimax rule revisited, Optim. 71 (2021), no. 4, 877–905.

[13] S. Mirjalili, S.M. Mirjalili and A. Lewis, Grey wolf optimizer, Adv. Eng. Software 69 (2014), 46–61.

[14] L.H. Pedersen, A. Babu, A. Levine, Enhanced portfolio optimization, Financ. Anal. J. 77 (2021), no. 2, 124–151.

[15] M. Seltzer, Forbes, forbes magazine, www.forbes.com/sites/forbesfinancecouncil/2018/01/11/ premium-financerisks and-considerations/, (2018).

[16] W.F. Sharpe, Budgeting and monitoring pension fund risk, Financ. Anal. J. 58 (2002), no. 5, 74–86.

[17] G.A. Wurden, S.C. Hsu, T.P. Intrator, T.C. Grabowski, J.H. Degnan, M. Domonkos, P.J. Turchi, E.M. Campbell, D.B. Sinars, M.C. Herrmann and R. Betti, Magneto-inertial fusion, J. Fusion Energy 35 (2016) no. 1, 69–77.

[18] L. Zhihuan, L. Yinhong and D. Xianzhong, Non-dominated sorting genetic algorithm-II for robust multi-objective optimal reactive power dispatch, IET Gen. Transmis. Distrib. 4 (2010), no. 9, 1000–1008.

[19] E. Zitzler, M. Laumanns and L. Thiele, SPEA2: Improving the strength Pareto evolutionary algorithm, TIK-report 103 (2001).
Volume 14, Issue 2
February 2023
Pages 167-174
  • Receive Date: 12 February 2022
  • Revise Date: 22 April 2022
  • Accept Date: 08 May 2022