Publication of the journal

The section is currently being updated

Special recommendation algorithms predict the preferences of e-com-merce system users, which facilitate decision making in choosing the proposed product. At the core of the e-commerce system is a computing system in which the principles of information storage are not always optimized for the operation of recommender algorithms. In this work, an algorithm for creating a surrogate key for indexing recommender system objects by popularity level is proposed in order to speed up the data sampling process by reducing the number of accesses to the storage medium and the query runtime. The key ensures that products are ranked based on user preferences, which allows for consistent access to data and faster loading of the most requested products. Various recommender algorithms that work with significant amounts of data are considered. The main criteria for choosing a method for constructing a surrogate index are its performance and ability to work with many alternatives and a large number of indicators. It has been proposed to use one of the TOPSIS multi-criteria decision-making methods to rank recommendation objects.
Mihail S. Chipchagov
Financial University under the Government of the Russian Federation, Russia, 125993, Moscow, Leningradsky ave., 49
Evgeny I. Kublik
Financial University under the Government of the Russian Federation, Russia, 125993, Moscow, Leningradsky ave., 49
Vladimir A. Popov
Military Academy of the Strategic Missile Forces named after Peter the Great, Russia, 143900, Moscow region, Balashikha, Karbyshev st., 8

124498, Moscow, Zelenograd, Bld. 1, Shokin Square, MIET, editorial office of the Journal "Proceedings of Universities. Electronics", room 7231

+7 (499) 734-62-05
magazine@miee.ru