Toward Recommender Systems Scalability and Efficacy

Abstract

Recommender systems play a key role in many branches of the digital economy. Their primary function is to select the most relevant services or products to users’ preferences. The article presents selected recommender algorithms and their most popular taxonomy. We review the evaluation techniques and the most important challenges and limitations of the discussed methods. We also introduce Factorization Machines and Association Rules-based recommender system (FMAR) that addresses the problem of efficiency in generating recommendations while maintaining quality.