A Systematic Literature Review on Deep Learning Approaches for Cloud Service Recommender Systems

Deep Learning (DL) offers a promising solution for cloud service recommender systems (CSRS) by addressing data sparsity issues and helping users overcome cold-start problems while managing dynamic preferences. The study follows the PRISMA 2020 guidelines in conducting a systematic literature review (SLR) of DL-based CSRS advancements from 2019 to 2025. The research started with 412 electronic records from Scopus, ScienceDirect, Springer, Wiley, and other sources before completing thorough screenings that narrowed the search to 23 appropriate studies. The integration of hybrid neural networks, along with attention mechanisms and knowledge graph integration, demonstrates improved accuracy for implementing the multi-criteria recommendations based on the quality-of-service prediction, the resource allocation, and the personalised service selection. Real-time scalability limitations and constraints regarding explainability remain despite current developments. Future research should examine federated learning systems and edge-cloud integration elements with ethical AI frameworks in place. The review delivers a structured overview that guides researchers and practitioners who want to enhance cloud service recommendations by employing modern methodologies.