Bayesian Neural Hawkes Process for Event Uncertainty Prediction

TL;DR

This paper introduces the Bayesian Neural Hawkes Process, a model that combines neural networks and Bayesian methods to improve event time prediction and uncertainty quantification in event data modeling.

Contribution

It proposes a novel Bayesian neural point process model that enhances uncertainty estimation and extends to spatio-temporal event modeling.

Findings

Significantly improves event time prediction accuracy.

Provides better uncertainty quantification over predictions.

Demonstrates effectiveness on both simulated and real datasets.

Abstract

Event data consisting of time of occurrence of the events arises in several real-world applications. Recent works have introduced neural network based point processes for modeling event-times, and were shown to provide state-of-the-art performance in predicting event-times. However, neural point process models lack a good uncertainty quantification capability on predictions. A proper uncertainty quantification over event modeling will help in better decision making for many practical applications. Therefore, we propose a novel point process model, Bayesian Neural Hawkes process (BNHP) which leverages uncertainty modelling capability of Bayesian models and generalization capability of the neural networks to model event occurrence times. We augment the model with spatio-temporal modeling capability where it can consider uncertainty over predicted time and location of the events. Experiments on simulated and real-world datasets show that BNHP significantly improves prediction performance and uncertainty quantification for modelling events.