A Hybrid Collaborative Filtering Recommendation Algorithm Based on University-Enterprise Matching Degree
Minghui Ma, Mingcong Wang · 2024
In recent years, the country has continuously promoted industry-academia collaboration. During the development of such collaborations, universities and enterprises face the dilemma of "who should we cooperate with?" To address this issue, this paper proposes a hybrid collaborative filtering recommendation algorithm based on university-enterprise matching. First, the matching degree between universities and enterprises is calculated based on their multi-dimensional features for recommendation. Then, the matching degree is used to fill the rating matrix, alleviating the data sparsity problem in collaborative filtering, followed by collaborative filtering recommendation. Finally, a hybrid recommendation is made based on the results of both recommendations. Experimental results show that the proposed algorithm performs well in terms of accuracy, recall, and F1 score, providing effective decision support for industry-academia cooperation.