Trading Strategy Based on Sentiment Analysis of the News

Student: Barkhatov Stepan

Educational Programme: Strategic Corporate Finance (Master)

Year of Graduation: 2021

In this paper we have attempted to create a trading strategy based on automated analysis of financial news. Core of the strategy consists of two models: one for sentiment analysis and another for determining trade closure moment. Sentiment analysis of news is done with pre-trained XLM-RoBERTA language model and fine-tuned with hand-made labeled data set of financial abstracts. We achieve classification accuracy of 72.3%. After that sentiment signal together with 10 variables based on technical indicators, are inputed in the Random Forest for evaluating exit decision. Strategy is back-tested on a group of Russian stocks over the period of 2012-2019. It demonstrated good results, yielding 36% annual return, which is significantly larger than 7.6% gained by MOEX total return index.

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