Matrix Factorization Based on Deep Learning for Collaborative Filtering

Student: Rubtsov Vasiliy

Educational Programme: Data Science (Master)

Final Grade: 7

Year of Graduation: 2017

Modern recommender system either not fully used all available information, or are built using several models (“stacking”), when the input of one model is the outputs of others. Such approaches are either not to complete in the sense of using useful information or not convenient due to alternate training models. In this paper, attempts are being made to overcome the shortcomings of these approaches by developing the architecture of recommender system in the form of a neural network. The methods of matrix factorization via neural networks are implemented, as well as some of their generalizations used in recommender systems.

Full text (added May 30, 2017)

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