CASR: A Collaborative Attention Model for Session-based Recommendation

Today the technological society is developing quickly, recommendation system is becoming an increasingly important technology. Session-based recommendation systems have become a hot research topic due to their ability to provide recommendations for anonymous users. Traditional session-based recommendation systems have some limitations. They either lack the ability to learn complex dependencies or only focus on the current session without explicitly considering collaborative information. We propose a collaborative attention for session-based recommendation model called CASR, which can mine users' long-term and short-term preferences to obtain users' real intention by using the close interaction relationship in time structure. We first model a Gate Recurrent Unit (GRU) framework with attention mechanism to obtain short-term preferences of users in a period of the time. Then, we propose a collaborative session search strategy and design a neighbor session search algorithm. It can not only obtain users' long-term preferences, but also alleviate the sparseness of the original session data to a certain extent. Finally, we use the capsule network with update strategy to get better prediction results. Extensive experiments on two real datasets show that our CASR model outperforms many mainstream methods.