Recommendation of Relevant News Resources Based in Machine Learning Techniques

Student: Don Vitaliy

Educational Programme: Data Science (Master)

Year of Graduation: 2018

In this thesis work analyzes the methods of recommendations of news resources. News quickly out of date. The purpose of the work is to apply existing reference models in dataset of news resources and assess the quality of their work. The following algorithms were used to recommend the news: PureSVD, ImplicitALS, LightFMWrapper, PopularityModel, RandomModel. To measure the quality were used: F-measure, precision, recall, nDCG (Normalized Discounted Cumulative Gain). Results of research: ImplicitALS was the best, followed by PureSVD, PopularityModel, LightFMWrapper, RandomModel. There were also tests on real users, where recommendations were displayed in a special recommendation block. The quality metric was ctr (the ratio of the number of clicks on an article to its impressions in the recommendation block). Results of tests: PureSVD was the best, followed by ImplicitALS, PopularityModel, LightFMWrapper, RandomModel.

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