Learning user preferences from Multi-Contextual Sequence influences for next POI recommendation

The recommendation of the next Point of Interest (POI) has attracted significant attention within the domain of POI recommendations in recent years. Existing methods for next POI recommendation are built on the original check-in sequences of users. Despite effectiveness, the original check-in sequences mix the influences of different contextual factors, which inevitably weakens the model ability of learning user preferences from the complex contextual information. To overcome this issue, we propose a novel Multi-Contextual Sequence-based Attention Network (MCSAN) for next POI recommendations. MCSAN first develops a new con-textual influence-based sampling strategy, which can transform the original check-in sequences into a series of contextual information-aware subsequences. Moreover, the constructed subsequences meticulously capture the impacts of various contextual information from the original check-in sequences. Then, MCSAN leverage the attention-based neural network to learn the representations of POIs from the generated subsequences. Finally, MCSAN develops a new feature fusion method that extracts user preferences from the learned POI presentations adaptively. Extensive experiments conducted on real-world datasets indicate the effectiveness of our proposed MCSAN for the next POI recommendation task, compared to recent representative methods.