The Recommendation System or the personalization system in social networks like Facebook plays vital role in product Marketing. People are mostly addicted nowadays over social networks such as Facebook, Twitter, Instagram, and so on. Thus, the data gathered from social networks like Facebook can be leveraged for recommendation systems or any other systems that requires knowledge about users. In social networks like Facebook, users reveal considerable information about their preferences, feelings, activities, etc. This information can be very valuable in determining the actual needs and preferences of users. The main objective of this research is to design and develop a recommendation system for social networks through community detection especially in Facebook. Communities are mined by the influential algorithm, that can be one of the powerful algorithm to mine out the perfect community to forecast the products. In this paper, we study and analyze various clustering techniques used for product recommendation using social information, which are used to identify the concept to address the data sparsity problem, cold start issues, and in turn to improve the prediction accuracy for product recommendation.
S et al. (Mon,) studied this question.