A Hybrid Recommender Algorithm Based on an Improved Similarity Method

Abstract

Recommendation systems have achieved widespread success in E-commerce nowadays. There are several evaluation metrics for recommender systems, such as accuracy, diversity, computational efficiency and coverage. Accuracy is one of the most important measurement criteria. In this paper, to improve accuracy, we proposed a hybrid recommender algorithm by an improved similarity method (ISM), combining demographic recommendation techniques and user-based collaborative filtering (CF) algorithms. Experiments were performed to compare the present approach with the other classical similarity measures based on the MovieLens dataset. The Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) values show the superiority of the proposed algorithm.