Synergetic Learning of Heterogeneous Temporal Sequences for Multi-Horizon Probabilistic Forecasting

TL;DR

This paper introduces VSMHN, a deep generative model that captures complex relationships between synchronous time-series and asynchronous events, improving multi-horizon probabilistic forecasting accuracy.

Contribution

It presents a novel variational synergetic network combining deep point processes and RNNs, with tailored encoding and training schemes for heterogeneous sequences.

Findings

Model achieves more accurate probabilistic forecasts.

Effective training with stochastic variational inference.

Model captures asynchronous event influences on time-series.

Abstract

Time-series is ubiquitous across applications, such as transportation, finance and healthcare. Time-series is often influenced by external factors, especially in the form of asynchronous events, making forecasting difficult. However, existing models are mainly designated for either synchronous time-series or asynchronous event sequence, and can hardly provide a synthetic way to capture the relation between them. We propose Variational Synergetic Multi-Horizon Network (VSMHN), a novel deep conditional generative model. To learn complex correlations across heterogeneous sequences, a tailored encoder is devised to combine the advances in deep point processes models and variational recurrent neural networks. In addition, an aligned time coding and an auxiliary transition scheme are carefully devised for batched training on unaligned sequences. Our model can be trained effectively using stochastic variational inference and generates probabilistic predictions with Monte-Carlo simulation. Furthermore, our model produces accurate, sharp and more realistic probabilistic forecasts. We also show that modeling asynchronous event sequences is crucial for multi-horizon time-series forecasting.