Stochastic Recurrent Neural Network for Multistep Time Series Forecasting

TL;DR

This paper introduces a stochastic recurrent neural network that incorporates latent variables into its transition function, enabling improved multistep time series forecasting across diverse domains.

Contribution

It proposes a novel stochastic adaptation of RNNs using variational Bayes, enhancing modeling of complex temporal dynamics in multistep forecasting tasks.

Findings

Outperforms deterministic RNNs on multiple datasets

Effective in finance and healthcare time series

Captures stochasticity in temporal evolution

Abstract

Time series forecasting based on deep architectures has been gaining popularity in recent years due to their ability to model complex non-linear temporal dynamics. The recurrent neural network is one such model capable of handling variable-length input and output. In this paper, we leverage recent advances in deep generative models and the concept of state space models to propose a stochastic adaptation of the recurrent neural network for multistep-ahead time series forecasting, which is trained with stochastic gradient variational Bayes. In our model design, the transition function of the recurrent neural network, which determines the evolution of the hidden states, is stochastic rather than deterministic as in a regular recurrent neural network; this is achieved by incorporating a latent random variable into the transition process which captures the stochasticity of the temporal dynamics. Our model preserves the architectural workings of a recurrent neural network for which all relevant information is encapsulated in its hidden states, and this flexibility allows our model to be easily integrated into any deep architecture for sequential modelling. We test our model on a wide range of datasets from finance to healthcare; results show that the stochastic recurrent neural network consistently outperforms its deterministic counterpart.