Application of Deep Neural Nets for Company Financial Statements Analysis

Student: Aleksandr Demenev

Supervisor: Valeriya Vladimirovna Lakshina

Educational Programme: Business Analytics in Economics and Management (Master)

Year of Graduation: 2024

The research is aimed at reviewing and applying existing deep learning models for analyzing financial statements of Russian companies. The paper presents a comparative analysis of modern language models and develops a prototype of its own algorithm for extracting useful information from financial reporting documents. The algorithm was trained and tested on data uploaded from an open Internet resource. The existing language models are used as the basis of the algorithm: "Yandex GPT" and "BERT". Thus, the result of the study is a script that allows you to process data from financial reporting documents and train a language model to predict the development of companies.

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