Session Based

Session-based recommendation (SBR) systems aim to predict a user's next interaction based solely on their current browsing session, without relying on user profiles or historical data. Current research heavily utilizes graph neural networks (GNNs) and transformer architectures to model complex item relationships within and across sessions, incorporating temporal information and addressing challenges like cold-start problems and popularity bias. These advancements improve recommendation accuracy and personalization, impacting various applications such as e-commerce, music streaming, and news portals by enhancing user experience and engagement.