A PRISMA-Based Systematic Review on Deep Learning in Multi-Criteria Recommender Systems
Ishwari Singh Rajput, Anand Shanker Tewari, Arvind Kumar Tiwari · Procedia Computer Science · 2025
Recommendation systems (RSs) are intelligent decision-support systems that take users’ preferences to propose items that might find interesting to the user. They also addresses the issue of overabundance of information. In comparison to traditional recommendation methods which utilise single-criteria ratings, multi-criteria recommendation systems(MCRS) employ multiple criterion ratings to estimate overall rating, have recently received a lot of interest in the RS research field. Furthermore, deep learning models in recent years shows promising results in a variety of research fields, including image processing, computer vision, natural language processing and pattern identification. Deep learning’s application in recommendation domain has been recently received a lot of attention. Nevertheless, despite several research attempts on recommendation systems, limited studies have been undertaken in the domain of deep learning-based multi-criteria recommender systems. This work presents a PRISMA methodological review of deep learning-based MCRSs to assist scholars and researchers in comprehending emerging trends and challenges in this field. This study looks at all of the multi-criteria recommendation methods that employ deep learning models. This study provides a comparative study of models which employ the same evaluation metrics and datasets. Furthermore, the difficulties and solutions that have been addressed in the literature are explored. Finally, several trends and future directions for researchers in this domain have been highlighted.