Modern data acquisition routinely produce massive amounts of event sequence
data in various domains, such as social media, healthcare, and financial
markets. These data often exhibit complicated short-term and long-term temporal
dependencies. However, most of the existing recurrent neural net
提出了一种利用 self-attention 机制进行 intensity function 拟合的 self-attentive Hawkes process 方法,相较于传统的统计方法和深度循环神经网络,该方法能更好地识别时间事件之间的复杂依赖关系,并且能够捕捉更长的历史信息,可以针对多变量事件序列进行有效的复杂模式预测。