期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2020
卷号：98
期号：7
页码：1101-1114
出版社：Journal of Theoretical and Applied
摘要：With the increase of information on the internet, more and more electronic data are appearing. Recommender systems were developed to help customers find related items or personalize services. Several online companies apply recommender systems to build up the relationship with users and enhance marketing and sales. Researchers and managers approve that the recommender system offers great opportunities in various domains. Thus, successful development of recommender systems for real-world applications are significant. The most widely used algorithms for recommender systems are categorized into the traditional recommendation and deep-based recommendation algorithms and hybrid recommendation approaches. There is a vital necessity to understand the recommendation system development way. So, this paper presents a structured framework that helps researchers and practical experts recognizing the development phases of the recommender system. The proposed framework is validated through a case study. Furthermore, this paper introduces a general classification scheme for all current recommendation approaches. A summary of historical past recommender system models provided in a way that facilitates understanding their target.
关键词：Recommender System (RS);Deep Learning (DL);Structured Framework;Sparsity;Cold Start;Scalability.
