A Survey on Friend Recommendation System
Jyoti Sharma, Pinky Tanwar · International journal of advance research and innovative ideas in education · 2016
Recommendation system is used to recommend resources that user may be interested in by mining user’s interests and/or preferences. Recommendation system matches user database with available items from item-database and suggest recommendation accordingly. Recommendation Systems provide users personalized assistances and information about products or services of interest to support their decision-making processes. Personalization deals with adapting to the individual requirements, interests, and preferences of each user. Most of the e-commerce sites e.g. Myntra.com, and social networking sites e.g. facebook.com have such recommendation systems. These systems serve two important tasks (1) to help users deal with the excess information by giving them appropriate recommendations (2) to help businesses make more profits by selling more products. Recommendation systems either recommend ‘people’ (partner, consultant, friend, etc.) or ‘things’ (movies, songs, books, etc.). Recommender systems typically create a list of recommendations in one of two ways through collaborative or content-based filtering. Collaborative filtering are relies on collecting and analyzing a large amount of information on users’ behaviors, activities and predicting what users will like based on their similarity to other users. Content-based filtering methods are based on a explanation of the item and a profile of the user’s preference. In this paper we will discuss about the friend recommendation system using different analyses.