FNHSM_HRS: Hybrid recommender system using fuzzy clustering and heuristic similarity measure
This addresses scalability and accuracy problems for users in recommender systems, but it is incremental as it builds on existing collaborative filtering methods.
The paper tackles scalability and accuracy issues in collaborative filtering recommender systems by proposing FNHSM_HRS, a hybrid system using fuzzy clustering and a new heuristic similarity measure, which shows improved performance on the MovieLens dataset as measured by MAE, Recall, Precision, and Accuracy.
Nowadays, Recommender Systems have become a comprehensive system for helping and guiding users in a huge amount of data on the Internet. Collaborative Filtering offers to active users based on the rating of a set of users. One of the simplest and most comprehensible and successful models is to find users with a taste in recommender systems. In this model, with increasing number of users and items, the system is faced to scalability problem. On the other hand, improving system performance when there is little information available from ratings, that is important. In this paper, a hybrid recommender system called FNHSM_HRS which is based on the new heuristic similarity measure (NHSM) along with a fuzzy clustering is presented. Using the fuzzy clustering method in the proposed system improves the scalability problem and increases the accuracy of system recommendations. The proposed system is based on the collaborative filtering model and is partnered with the heuristic similarity measure to improve the system's performance and accuracy. The evaluation of the proposed system based results on the MovieLens dataset carried out the results using MAE, Recall, Precision and Accuracy measures Indicating improvement in system performance and increasing the accuracy of recommendation to collaborative filtering methods which use other measures to find similarities.