Recommending Friends on Social Network with Artificial Intelligence Approach

In this smart world to connect from the world we use social network. In the old times the people used be friend with their neighbors colleagues and any other person related to them. When the people shifted to the social networking the domain of friends increased a lot and a most important feature is the friend recommendation as the system suggests friends to the used based on the mutual friends, this technique is called as the social graphs. Social graphs may or may not be the most appropriate technique to reflect a users preferences on friend selection as such type of friend selection is not done in real world. In this project we present an AI based friend recommendation system for social networks, which recommends friends to users based on their life styles instead of social graphs. It majorly takes the advantage of users Post Comments and profile, all these are rich in information. It discovers the lifestyle of the user from user-centric data and measures the similarity with the other users and we recommend them. If the average of the similarity is greater than the mean of similarities. AI based Friend recommendation system returns a list of people with highest recommendation scores to the query user. The results show that the recommendations accurately reflect the preferences of users in choosing friends.