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

Stock Market Prediction Service Based on Social Network Data

Student: Ghazal Abdulrahim

Supervisor: Sergey Viktorovich Zykov

Faculty: Faculty of Computer Science

Educational Programme: System and Software Engineering (Master)

Final Grade: 9

Year of Graduation: 2020

Stock markets are one of the most complex phenomena in our world, because every aspect of public and sometimes private lives can affect its performance and behavior. Due to this seeming randomness, and its huge impact on world economies, the discovery and employment of historical patterns that may emerge of this behavior to predict its future behavior was the attraction for many experts, and with the emergence of social media, became even more data-oriented and data-hungry. This may come as a result to the simple observation that normal people usually express their thoughts and opinions about a company or the whole market’s activity on these networks, and this spurred a lot of research into using social media to predict the future in general and in the stock markets specifically. In this thesis, we try to support the research by implementing a set of tools that can save the researcher time and effort when they try to address this problem. These tools are built using the Microservices architecture, as a group of small, independent, loosely coupled, easily maintained services that interact with each other using web protocols. This supports scaling these services and further development by other researchers, as these services can be tweaked to fit other research prediction purposes, like predicting sales, resources, or any other social indicator that changes with time. The process of predicting happens over several phases. First, we collect the data based on several chosen criteria, then we clean this data from anomalies and noise. Next step would be processing it, so we can convert it to features that can be used to build a model to represent the market’s behavior. The prediction happens when we use this model to give the future values of the chosen time series (either the stock market index, or a company’s stock prices over time).

Full text (added May 22, 2020)

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