Attentive Neural Point Processes for Event Forecasting
Keywords:Time-Series/Data Streams, Web Personalization & User Modeling, Mining of Spatial, Temporal or Spatio-Temporal Da, Recommender Systems & Collaborative Filtering
AbstractEvent sequence, where each event is associated with a marker and a timestamp, is increasingly ubiquitous in various applications. Accordingly, event forecasting emerges to be a crucial problem, which aims to predict the next event based on the historical sequence. In this paper, we propose ANPP, an Attentive Neural Point Processes framework to solve this problem. In comparison with state-of-the-art methods like recurrent marked temporal point processes, ANPP leverages the time-aware self-attention mechanism to explicitly model the influence between every pair of historical events, resulting in more accurate predictions of events and better interpretation ability. Extensive experiments on one synthetic and four real-world datasets demonstrate that ANPP can achieve significant performance gains against state-of-the-art methods for predictions of both timings and markers. To facilitate future research, we release the codes and datasets at https://github.com/guyulongcs/AAAI2021\_ANPP.
How to Cite
Gu, Y. (2021). Attentive Neural Point Processes for Event Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 35(9), 7592-7600. https://doi.org/10.1609/aaai.v35i9.16929
AAAI Technical Track on Machine Learning II