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

Attacking the Cold Start Problem in Web-Advertising Service with Social-Network Data

Student: Nikolich Stefan

Supervisor: Dmitry I. Ignatov

Faculty: Faculty of Computer Science

Educational Programme: Applied Mathematics and Information Science (Bachelor)

Year of Graduation: 2018

In recent years, number of Internet users that have been practicing the usage of various online stores or other Internet services is increasing. Thus, there is a growing demand for recommendation systems for those services. Since many types of implementations of those recommendation systems are heavily based on the history of interactions between users and objects, there are problems which often arise when this history does not exist. In such cases, services often use initial data about user. For example: the data specified when registering on the resource. However, in recent years an increasing number of users have been authorized into Internet services through various social networks. This opens a great potential for improving the recommendations to the above-described problematic users. In this paper, we solve the problem of giving recommendations to such users on the basis of social network data for the service of advertisements. In particular, detecting the dependency between the user's data in the social network and his favorite category on the service of advertisements. A model of machine learning based algorithm using social network data (including the generated features) was constructed and results were obtained. Results are exceeding the random choice model but proved to be inferior to the existing model built on collaborative filtering.

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