The Neural Hawkes Process: A Neurally Self-Modulating Multivariate Point Process

TL;DR

This paper introduces a neural network-based multivariate point process model that captures complex event dependencies over continuous time, improving prediction accuracy and handling missing data effectively.

Contribution

It presents a novel continuous-time LSTM-based generative model for multivariate point processes that models event dependencies dynamically.

Findings

Achieves competitive likelihood scores on real and synthetic data.

Handles missing data effectively in event sequence modeling.

Demonstrates improved predictive accuracy over existing methods.

Abstract

Many events occur in the world. Some event types are stochastically excited or inhibited---in the sense of having their probabilities elevated or decreased---by patterns in the sequence of previous events. Discovering such patterns can help us predict which type of event will happen next and when. We model streams of discrete events in continuous time, by constructing a neurally self-modulating multivariate point process in which the intensities of multiple event types evolve according to a novel continuous-time LSTM. This generative model allows past events to influence the future in complex and realistic ways, by conditioning future event intensities on the hidden state of a recurrent neural network that has consumed the stream of past events. Our model has desirable qualitative properties. It achieves competitive likelihood and predictive accuracy on real and synthetic datasets, including under missing-data conditions.