Multivariate Forecasting of Stock Prices by Machine Learning

Student: Grigoreva Anna

Faculty: HSE Tikhonov Moscow Institute of Electronics and Mathematics (MIEM HSE)

Educational Programme: Applied Mathematics (Bachelor)

Final Grade: 9

Year of Graduation: 2024

Time series forecasting is important in various fields for decision making. In particular, financial time series such as stock prices can be difficult to predict because it is difficult to forecast short and long-term time dependencies between data points. There are various methods for short-term and long-term forecasting, but the quality of any given method will depend heavily on the data. The method that was proposed in this work involves primary clusterization of data based on certain patterns of stock time series behavior, which helps to select a method for forecasting with the highest quality. In our experiments, we demonstrated the success of the proposed method in comparison with widely accepted machine and deep learning methods for predicting changes in daily stock prices from the S&P 500 index

Full text (added May 17, 2024)

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses