Russian Federation
The article presents a comparative analysis of machine learning models for stock price forecasting. The process of algorithmic trading is characterized. The use of artificial intelligence in the stock market, the advantages and disadvantages of its application are considered. The models of the machine learning model are selected: linear regression and random forest, and their characteristics are given. Metrics for assessing the quality of forecasts are defined and their mathematical description is presented. Training and testing of models were performed, predicted values were obtained, and the necessary metrics were found. All calculations, analysis, and machine learning are performed in the Python programming environment using the Pandas, Numpy, Matplotlib, and Sklearn libraries. As a result, the random forest model turned out to be the most reliable, taking into account high accuracy and error minimization, for the linear regression model, the standard error and the average absolute error are almost 90% greater
linear regression, random forest, machine learning, quote forecasting, algorithmic trading
1. Bogatyrev S.Yu. [i dr.]. Mashinnoe obuchenie v finansah :uchebnik [Elektronnyy resurs]. — M.: Prometey, 2024. 224 s.
2. Kremer N.Sh. Ekonometrika [Tekst] / N.Sh. Kremer, B.A. Putko. — M.: YuNITIDANA, 2010. — 328 s.
3. Limanovskaya O.V. Osnovy mashinnogo obucheniya [Tekst] / O.V. Limanovskaya, T.I. Alfer'eva. — Ekaterinburg: Izdvo Ural. unta, 2020. — 88 s.
4. Malyhin E.M. Algoritmicheskiy treyding dlya professionalov [Tekst] / E.M. Malyhin. — SPb.: BHVPeterburg, 2021. — 176 s.
5. Harrison M. Mashinnoe obuchenie: karmannyy spravochnik «Kratkoe rukovodstvo po metodam strukturirovannogo mashinnogo obucheniya na Python» [Tekst] / M. Harrison. — SPb.: Dialektika, 2020. — 320 s.
6. Yansen S. Mashinnoe obuchenie dlya algoritmicheskoy torgovli na finansovyh rynkah. Praktikum [Tekst] / S. Yansen. — SPb.: BHVPeterburg, 2019. — 560 s.
7. Krauss C., Do X.A., Huck N. Deep neural networks, gradientboosted trees, random forests: Statistical arbitrage on the S&P 500. European Journal of Operational Research (2016), 259(2), 689–702. DOI:https://doi.org/10.1016/j.ejor.2016.10.031/ URL: https://www.scihub.ru/10.1016/j.ejor.2016.10.031?ysclid=lw tkxebont933507928 (accessed 28 May 2024).
8. Hong K. Modelling Intervalling Effect of High Frequency Trading on Portfolio Volatility. Theoretical Economics Letters, October 2019, vol. 9, no. 7. URL: https://www.scirp.org/ journal/paperinformation?paperid=95423 (accessed 28 May 2024).
