Enhanced Recommendation Systems: A Survey on the Impact of Auxiliary Information

Abstract

In the age of big data, recommendation systems have become a critical tool for helping users navigate the overwhelming amount of online information. Enhanced recommendation systems take this one step further, leveraging the latest algorithms and data-driven insights to deliver highly personalized and relevant recommendations. This research paper provides a comprehensive overview of the recent progress in enhanced recommendation systems, covering the current state-of-the-art techniques and discussing the opportunities and challenges practitioners face. The article explores a range of approaches, including deep learning techniques and hybrid models that integrate both user and item data, and presents the essential concepts, methods, and applications driving the advancement of recommendation systems. We recognize the pressing hurdles in the field as sparsity and diversity, thereby focusing on intentbased models that exploit the additional/auxiliary information by aggregating implicit feedback from user-item interactions. We have gone one step further by compiling the benchmarks in the field, enabling new researchers to explore and innovate at a much more thoughtful and faster pace