• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Student
Title
Supervisor
Faculty
Educational Programme
Final Grade
Year of Graduation
Maksim Pershin
Building A Predictive Model for Valuing Securities By Analyzing Unstructured News Information
Economics
(Bachelor’s programme)
2018
The paper discusses the basics of work and the theoretical description of Long shot-term memory of neural networks and Biderectional long shot-term memory of neural networks.

The main ways of processing unstructured information in similar tasks are considered.

As the data in the practical part of the study, the texts from the news agency Vedomosti were used. Data was collected on the prices for Gazprom shares, as well as the necessary data for the calculation of EV / EBITDA and P / CF multiples.

In the framework of this final qualifying work, a predictive model for valuing securities was created using unstructured news information analysis using BLSTM and LSTM networks. An algorithm for the representation of textual information in a vector space is given. The model showed fairly good results in the classification problem (accuracy = 0.5595).

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