An approach to reduce cold start in compound recommender systems using semantic technology and social networks

today, the effort to build a recommender system with low precision and high speed in all conditions has become one of the most popular fields ofresearch. Due to high percentage error, a basic method to build such systems is not usually being applied. In this research, two methods have been suggested in order toimprove recommendations in recommender systems. The first suggested approach is a user-base method which predicts rates using similarity detection betweentarget user and its neighbours. The second proposed approach is an item -base method which uses similaritydetection between items, in order to predict possible rates of target user. Finally, the results show that combining semantic technology with social networks hasreduced issues such as cold start and generally data sparsity in recommender systems.

Keywords:

Recommender systems , user – base algorithm , item – base algorithm , semantic web , social networks