Enhancing Group Recommendation Using Attention Mechanisam

As indulging in group activities is prevalent in people’s day-to-day life, suggesting or recommending the information to a group of people has become a crucial task. Due to its importance in satisfying the group members, the recommendation for the group has captivated significant research efforts. The primary goal of group recommendation is aggregating the group members’ interests to infer the group decision. In this work, Group Recommendation using the attention mechanism model (GRAM) is built and optimized to address the issue of preference aggregation, which uses a neural attention network and neural collaborative filtering framework. The attention component uses to capture the effect of every member within the group. A neural collaborative filtering framework utilizes to learn the group-item interactions in the data. The GRAM model experiments on the CAMRa2011 data set. The model evaluation uses the various metrics, the Hit ratio and Normalized Discounted Cumulative Gain.