Optimization method of investment package based on Markowitz portfolio theory

Objective. The aim of the study is to implement and evaluate the optimization method based on the Markowitz portfolio theory. Method. The model is built using the Python programming language and the necessary libraries. Also, to solve the problem, the principles of financial theory were used - the calculation of the risk of the purchased asset, portfolio diversification and the principle of optimality. These principles form the basis of financial theory and help you make informed decisions related to investment, financing, and risk management. Result. A model of the program has been compiled, which accepts historical data on changes in the value of shares of different companies as input. After that, the optimal portfolio is calculated and displayed in the terminal of the user-investor. Markowitz portfolio theory helps to determine the optimal portfolio that provides the maximum return for a given level of risk or the minimum risk for a given return. The optimal portfolio is tangent to the risk-free asset curve and is the best choice for the investor, given his preferences. Conclusion. The method of forming an investment portfolio developed by Harry Markowitz, aimed at the optimal choice of assets, proceeds from the required ratio of profitability/risk. The ideas formulated by him form the basis of modern portfolio theory. Portfolio theory Markowitz defines an efficient set, which is all possible portfolios with different combinations of assets that provide the same level of risk. Investors can choose portfolios from this set depending on their personal goals and limitations. The variety of assets in a portfolio helps reduce the overall level of risk and improve the risk-reward ratio.

1. Gitman L. J., Dzhonk M. D. Fundamentals of investment. Per. from English. M Delo, 1997;1008. (In Russ)

2. Krass M.S., Chuprynov B.P. Mathematics for economists. - St. Petersburg, Peter, 2009; 251. (In Russ)

3. Yu. F. Kasimov. Fundamentals of the theory of the optimal portfolio of securities - M: Information and Publishing House “Filin”, 1998;144. (In Russ )

4. Volkova P.A., Shipunov A.B. Statistical data processing in educational research work. M.:Forum, 2012; 96. (In Russ)

5. Bol’shakov A. Methods for processing multidimensional data and time series. M.: GLT, 2007; 522.(In Russ)

6. Venikov V.A., Venikov G.V. Theory of similarity and modeling. M.: Higher school. 1984; 439 (In Russ)

7. Jansen S. Hands-On Machine Learning for Algorithmic Trading - Birmingham: Packt Publishing, 2019; 686.

8. Hilpisch Y. Python for Finance: Analyze Big Financial Data - Sebastopol: O’Reilly Media, 2015; 606.

9. Bulavin L.A. Computer modeling of physical systems: textbook / L.A. Bulavin, N.V. Vygornitsky, N. I. Lebovka - Dolgoprudny: Intelligence, 2011; 349. (In Russ)

10. Morozov V.K. Modeling of information and dynamic systems: a textbook for universities / V.K. Morozov, G.N. Rogachov - M .: Academy, 2011; 377.(In Russ)

11. Emelyanov V. V., Kureichik V. V., Kureichik V. M. Theory and practice of evolutionary modeling. – M.: Fizmatlit, 2003;. 432. (In Russ)

12. McKinney W. Python and data analysis - Moscow: DMK Press, 2015; 482. (In Russ)

13. Grigoriev, A.A. Methods and algorithms for data processing: Textbook M.: Infra-M, 2018; 384. (In Russ)

14. Ma Weiming J. Mastering Python for Finance - Birmingham: Packt Publishing, 2019; 428.

15. Ostroukh, A.V. Input and processing of digital information. Textbook. M.: Academia, 2017; 384.(In Russ)

16. Peter Bruce Practical Statistics for Data Scientists: 50+ Essential Concepts Using R and Python - O’Reilly Media, 2017; 320.

17. Seiersen R. The Metrics Manifesto: Confronting Security with Data - Wiley, 2022; 320.

18. Peter C. Bruce Data Mining for Business Analytics:Concepts, Techniques, and Applications Wiley, 2016; 560.