Learning Interpretable Deep State Space Model for Probabilistic Time Series Forecasting
This work addresses risk management in decision-making for domains like finance or healthcare, but it is incremental as it builds on existing deep state space models.
The paper tackles probabilistic time series forecasting by proposing a deep state space model with an automatic relevance determination network to incorporate exogenous variables, resulting in accurate and sharp forecasts with realistic uncertainty that increases over time.
Probabilistic time series forecasting involves estimating the distribution of future based on its history, which is essential for risk management in downstream decision-making. We propose a deep state space model for probabilistic time series forecasting whereby the non-linear emission model and transition model are parameterized by networks and the dependency is modeled by recurrent neural nets. We take the automatic relevance determination (ARD) view and devise a network to exploit the exogenous variables in addition to time series. In particular, our ARD network can incorporate the uncertainty of the exogenous variables and eventually helps identify useful exogenous variables and suppress those irrelevant for forecasting. The distribution of multi-step ahead forecasts are approximated by Monte Carlo simulation. We show in experiments that our model produces accurate and sharp probabilistic forecasts. The estimated uncertainty of our forecasting also realistically increases over time, in a spontaneous manner.