LAUSR

Currently in many real time applications, recommender systems play a prominent role in helping the customers by selecting the most suitable products of their requirements. Generally the scheme of recommending the products is observed as single individual task. To enhance this task, the collaborating filtering is used as more effective charge in many situations. One of the major issues of the recommender system is difficult in learning the behavior of the group of the products and nature of the customers. Also in this internet era, the data collected day by day keeps on increasing and leads to information overloaded issue .Under this situation it is recommended to propose a novel collaborative filtering based methodology named ‘Hellinger Coefficient Based Collaborative Filtering (HCBCF)’ to search, find and rate the recommending products. The efficiency of the proposed method is evaluated on movie lens and Netflix recommendation datasets, and also this proves to be superior among other existing recommendation algorithms on comparing its efficiency metrics.