350 rub
Journal Information-measuring and Control Systems №5 for 2023 г.
Article in number:
Portfolio optimization with machine learning
Type of article: scientific article
DOI: https://doi.org/10.18127/j20700814-202305-06
UDC: 519.67
Authors:

M.V. Khramtsov1, R.A. Kochkarov2, A.A. Rylov3

1−3 Financial University under the Government of the Russian Federation (Moscow, Russia)

1 maks_future@mail.ru, 2 rkochkarov@fa.ru, 3arylov@fa.ru

Abstract:

In this problem, an approach is proposed to optimize the portfolio by the number of securities booms and preserve their composition using machine learning algorithms. It is proposed to predict the value of securities to make a decision on changing the share in the portfolio. Consider well-known algorithms and propose an automated algorithm for optimizing a portfolio of securities based on machine learning methods.

Existing principles of operation of trading algorithms are considered. The main directions of their application in investment activity are given. Theoretical aspects of portfolio optimization are considered, the distinctive features of trading advisors and their areas of application are highlighted. A model using a neural network is proposed.

The proposed neural network model predicts the future closing price of an asset. For the model, tests were made for the accuracy of forecasting. The model has the ability to quickly change the parameters in order to increase the accuracy of the forecast for a shorter period.

Pages: 48-55
For citation

Khramtsov M.V., Kochkarov R.A., Rylov A.A. Portfolio optimization with machine learning. Information-measuring and Control Systems. 2023. V. 21. № 5. P. 48−55. DOI: https://doi.org/10.18127/j20700814-202305-06 (in Russian)

References
  1. Brigham E.F., Houston  J.F. Fundamentals of Financial Management. Cengage Learning. 2015.
  2. Chan, Ernie. Algorithmic Trading. John Wiley & Sons. 2013.
  3. Kakimi mogut byt algoritmy dlya torgovli na birzhe: Bazovaya klassifikatsiya. URL: https://habr.com/ru/company/iticapital/blog/372019/ (data obrashcheniya: 02.06.2023). (in Russian)
  4. Lutz, Mark. Learning Python. O’Reilly Media, Inc. 2013.
  5. Algoritm formirovaniya investitsionnogo portfelya na osnove metoda Markovitsa i ego optimizatsiya po skorosti vypolneniya. URL: https://science-education.ru/ru/article/view?id=6399 (data obrashcheniya: 02.06.2023). (in Russian)
  6. Algoritmicheskii treiding, torgovye roboty. URL: https://www.metatrader5.com/ru/terminal/help/algotrading (data obrashcheniya: 02.06.2023). (in Russian)
  7. Investitsionnyi portfel svoimi rukami. URL: https://school.moex.com/articles/investicionnyj-portfel-svoimi-rukami (data obrashcheniya: 02.06.2023). (in Russian)
  8. Enin A.V. Optimizatsiya investitsionnogo portfelya po metodu Markovitsa. URL: https://habr.com/ru/articles/516236/ (data obrashcheniya: 02.06.2023). (in Russian)
  9. Bogomolov A.I., Kharitonova A.E. Ispolzovanie iskusstvennogo intellekta v ekonomike: problemy i perspektivy. Neirokompyutery: razrabotka, primenenie. 2023. T. 25. № 4. S. 16-23. DOI: https://doi.org/10.18127/j19998554-202304-03
Date of receipt: 08.08.2023
Approved after review: 22.08.2023
Accepted for publication: 02.10.2023