Financial Indicators Predictions Using Sentiment Analysis of News Streams

Student: Gareev Artem

Supervisor: Dmitry A. Romanov

Educational Programme: Business Informatics (Master)

Year of Graduation: 2019

This paper explores the possibilities of machine learning methods usage for business process improvement. One of the ways to support decision making in business processes is to build predictive mathematical models. The paper describes the developed model for predicting the Bitcoin prices movement based on the Twitter messages sentiment analysis. Analyzed scientific publications on the topic of work and highlighted the effective method of determining the tonality of the text and the predictions of the price movement of financial indicators. The process of building an experimental model for predicting the movement of Bitcoin price is considered, the results of testing the constructed model are given. It is shown that the analysis of the emotional coloring of the news flow allows us to predict the direction of price movement of a financial indicator with an accuracy of at least 72%.

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