Stock Prices Prediction Based on News Event Type Classification

Student: Kuznetsov Daniil

Faculty: St.Petersburg School of Economics and Management

Educational Programme: Economics (Bachelor)

Year of Graduation: 2021

In this paper we make an attempt to fulfill two eternal human wishes: the first is to predict the future and the second is to make the prediction profitable. Nowadays elaborated techniques of machine learning analysis make it possible to predict stock prices dynamics on the market. Stock prices as well as news texts can be used to solve this problem. Natural Language Processing (NLP) techniques are applicable to analyze text and event type described in news. This study investigates stock price prediction model based on automatic news event type detection and on selected technical indicators. The major result is that the prediction model has improved in terms of its evaluation metrics and profitability of proposed trading strategy by including news event type features generated by BERT classification network.

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