Improved Collaborative Filtering Recommender System Based on Hybrid Similarity Measures

Recommender Systems (RS) based on collaborative filtering has been successfully applied to provide relevant and personalized recommendations from an enormous amount of data in various domains. To achieve this, similarity measurements, such as the Pearson Correlation Coefficient (PCC), Cosine, and Jaccard, are used to compute the similarity between users or items based on correlations among user preferences from the user-item rating matrix. However, existing similarity metrics suffer from drawbacks emanating from data sparsity caused by insufficient number of transactions and feedback and scalability of the system’s ability to handle increasing amounts of data efficiently. The objective of this study is to improve the recommendation quality and increase the prediction accuracy by addressing the problems of similarity computation in collaborative filtering. This paper presents a hybrid similarity measure that combines Adjusted Triangle similarity, User Rating Preference behavior, and the Jaccard (ATURPJ) coefficient. The proposed hybrid similarity measures were evaluated on four widely used and publicly available datasets, MovieLens, FilmTrust, and CiaoDVD, using the predictive accuracy metrics of Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) and recommendation quality of Precision, Recall, and F-measure. The experimental results show that the proposed hybrid similarity measure significantly outperforms existing approaches with MAE of 0.547 and RMSE of 0.735 compared to the baseline of 0.707 and 0.903 respectively on ML-100k dataset. Overall, this approach has the potential to improve the quality of recommendation and accuracy of the prediction