• 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
Yuliya Zhosan
Data mining of human behavior in games
School of Applied Mathematics and Information Science
Bachelor’s programme
8
2014
Rapid computerization is one of the key features of the current stage of society evolution. The development of modern means of data receiving, storing, processing and transmission led to the accumulation of vast amounts of information about the various spheres of human life and society. Moreover, these data are constantly updated and timely analysis is critical to the normal functioning of many spheres of human life, whether they are economics, sociology or medicine.Traditional software engineering uses fairly simple analysis algorithms, which is rarely enough to get relevant results. Huge computational power of modern hardware is used with efficiency which is not very high.Machine learning is an example of new and more progressive approach to data analysis. It is a technology relating to the artificial intelligence. Machine learning explores algorithms for different computer models, capable of self-learning. This self-training is inductive, its main feature is searching for regularities in given empirical data.Inductive learning methods allows computers to operate with increasingly complicating algorithms of analysis and get more and more relevant results for the cases when human brain is unable to cope with large data flow.This work studies the applicability and computational efficiency of machine learning techniques in the field of economic analysis. It is shown, that the methods of machine learning can give results not worse than traditional econometric methods with their deductive technologies and approach "from model to data”. On the one hand, machine learning is suitable to obtain results similar to the testing of economic hypotheses. On the other hand, machine learning, as it uses the approach "from data to model", can detect correlations, which may indicate some regularities escaping notice of researcher-economists. The discovery of such regularities makes information about subject substantially more complete.The methods of machine learning are much more effective from the point of view of effort and time as well. From this point of view, their future development is likely to be impressively rapid.

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