Hybrid Collaborative Filtering Algorithm Based on Sparse Rating Matrix and User Preference

This study presents a hybrid collaborative filtering recommendation algorithm for sparse data (HCFDS) to increase the recommendation impact by addressing the problem of data sparsity in standard collaborative filtering methods. To begin, the similarity calculation divergence is evident in a data sparse environment due to the difference in user scoring standards and the rise in weight of the same score in the overall score. The user similarity algorithm IU-CS and item similarity algorithm II-CS are suggested in this work by incorporating the score difference threshold and the same score penalty factor, in order to address the deviation of similarity computation caused by the excessive dilation. Second, this work offers a filling optimization technique for score prediction to address the issue of missing score matrix data. The II-CS algorithm presented in this work is used to forecast the missing items in the scoring matrix first, and then, the user's preference score in the item category dimension is utilized to correct the score prediction value and fill the matrix. Finally, the IU-CS method presented in this work is used in this study to provide recommendations on the filled score matrix. Experiments indicate that, when compared to the preoptimization method and other algorithms, the optimized algorithm successfully solves the problem of data sparsity and the recommendation accuracy is considerably increased.