Event-based incremental recommendation via factors mixed Hawkes process

Incremental recommendation systems have garnered significant research interest since they ideally adapt to users' ongoing events (such as clicking, browsing, and reviewing) and recommend items without retaining the model. Many methods have tracked the event generation sequences for incremental recommendation. However, most existing models treat the event as a static snapshot or a black box, ignoring the underlying factors that may trigger the event generation. Underlying such inner factors can help RS reasonably and foreseeingly evaluate the potential items for the user next time. Along this vein, we propose the Factors Mixed Hawkes Process (FMHP) for event-based incremental recommendations. First, we extend each event to a notion of factor-driven event sequence. Next, we consider three factors that may influence the occurrence of an event: intrinsic intensity, external intensity, and historical intensity. An intrinsic intensity function, multi-type temporal attention, and a hybrid time decay function are incorporated in FMHP to evaluate the intrinsic, external, and historical intensity, respectively. In addition, an incremental updating strategy is implemented in FMHP, continuously updating event intensity as new events occur. We conduct extensive experiments on four public datasets (e.g., Amazon Beauty, LastFM, Movielens, and Amazon Book). Compared with state-of-the-art incremental recommendation methods, our proposed FMHP model achieves superior performance, with up to 9.77%, 9.35%, 9.32%, 10.10% w.r.t. HR, 8.86%, 10.26%, 9.81%, 9.38% w.r.t. NDCG, and 9.64%, 9.32%, 8.97%,9.85% w.r.t. Recall in Beauty, LastFM, MovieLens, and Book, respectively. Besides, the case study shows that the three factors in our proposed FMHP method play a vital role in triggering event generation.