Cloud services recommendation: Reviewing the recent advances and suggesting the future research directions

- Offering a systematic overview of the existing techniques in cloud recommender systems.
- Highlighting the advantages and disadvantages in the each domain.
- Exploring some of the primary challenges in the field of the recommender system.
- Presenting the guidelines for the existing challenges.
- Outlining the key areas where future research can improve the function of recommender systems.

Cloud computing systems provide a vast amount of various services, therefore it is difficult for a user to choose a suitable service. Cloud recommender systems are intelligent engines that suggest the best item for users in a cloud environment. Due to the importance of the recommender systems in the cloud environments, this study aimed to systematically investigate the articles and important mechanisms in recommender systems. In this regard, a systematic review of the recommender system's mechanisms which have been used in cloud computing was conducted. We classified the cloud recommender system's mechanisms into four main categories: collaborative filtering, demographic-based, knowledge-based and hybrid. Moreover, this study represented a systematic review and comparison of the above-mentioned techniques in terms of scalability, availability, accuracy, and trust attributes. The results of the present review revealed that previous studies contributed scalability and accuracy to the recommender system, but the contribution of the trust and security improvement has not been considerable well.