Long Horizon Forecasting With Temporal Point Processes

TL;DR

This paper introduces DualTPP, a novel model combining microscopic and macroscopic perspectives to improve long horizon event forecasting with marked temporal point processes, significantly outperforming existing methods.

Contribution

DualTPP is a new dual-component model that enhances long-term event prediction by jointly modeling granular event timings and aggregated counts.

Findings

Outperforms existing MTPP methods on long horizon forecasting

Achieves nearly tenfold reduction in Wasserstein distance

Effective across diverse real-world datasets

Abstract

In recent years, marked temporal point processes (MTPPs) have emerged as a powerful modeling machinery to characterize asynchronous events in a wide variety of applications. MTPPs have demonstrated significant potential in predicting event-timings, especially for events arriving in near future. However, due to current design choices, MTPPs often show poor predictive performance at forecasting event arrivals in distant future. To ameliorate this limitation, in this paper, we design DualTPP which is specifically well-suited to long horizon event forecasting. DualTPP has two components. The first component is an intensity free MTPP model, which captures microscopic or granular level signals of the event dynamics by modeling the time of future events. The second component takes a different dual perspective of modeling aggregated counts of events in a given time-window, thus encapsulating macroscopic event dynamics. Then we develop a novel inference framework jointly over the two models % for efficiently forecasting long horizon events by solving a sequence of constrained quadratic optimization problems. Experiments with a diverse set of real datasets show that DualTPP outperforms existing MTPP methods on long horizon forecasting by substantial margins, achieving almost an order of magnitude reduction in Wasserstein distance between actual events and forecasts.