Skip to content
DSML.KZ
Publications

Article · NEWS OF THE NATIONAL ACADEMY OF SCIENCES OF THE REPUBLIC OF KAZAKHSTAN · February 8, 2021

COMPARISON MODELS OF MACHINE LEARNING FOR MOVIE RECOMMENDATION SYSTEMS

A.Y. Zhubatkhan, Zholdas Buribayev, Sanzhar Aubakirov, M.D. Dilmagambetova, S.A. Ryskulbek

Sanzhar Aubakirov
Open via DOI

Abstract

The trend of the Internet makes the presentation of the right content for the right user inevitable. To this end, recommendation systems are used in areas such as music, books, movies, travel planning, e-commerce, education, and more. One of the most popular recommendation systems in the world is Netflix, which generated record profits during quarantine in the first quartile of 2020. The systematic approach of recommendations is based on the history of user selections, likes and reviews, each of which is interpreted to predict future user selections. This article provides a meaningful analysis of various recommendation systems, such as content-based, collaborative filtering and popularity. We reviewed 7 articles published from 2005 to 2019 to discuss issues related to existing models. The purpose of this article is to compare machine learning algorithms in the Surprise library for a recommendation system. Recommendation system has been implemented and quality has been evaluated using the MAE and RMSE metrics.

Recommender Systems and TechniquesAdvanced Bandit Algorithms ResearchInformation Retrieval and Search Behaviormovie recommendation systemcollaborative filteringcontent-based recommendation

More by Sanzhar Aubakirov