Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models

TL;DR

This paper introduces a novel approach using state-space models to simultaneously discover causal relations and improve forecasting in nonstationary time series, leveraging nonstationarity for better identifiability and adaptive prediction.

Contribution

The paper proposes a method that exploits nonstationarity within nonlinear state-space models to identify causal structures and enhance forecasting accuracy, which is a novel approach in this context.

Findings

Nonstationarity aids in causal structure identification.

Forecasting benefits from learned causal knowledge.

Experimental results validate the effectiveness of the proposed methods.

Abstract

In many scientific fields, such as economics and neuroscience, we are often faced with nonstationary time series, and concerned with both finding causal relations and forecasting the values of variables of interest, both of which are particularly challenging in such nonstationary environments. In this paper, we study causal discovery and forecasting for nonstationary time series. By exploiting a particular type of state-space model to represent the processes, we show that nonstationarity helps to identify causal structure and that forecasting naturally benefits from learned causal knowledge. Specifically, we allow changes in both causal strengths and noise variances in the nonlinear state-space models, which, interestingly, renders both the causal structure and model parameters identifiable. Given the causal model, we treat forecasting as a problem in Bayesian inference in the causal model, which exploits the time-varying property of the data and adapts to new observations in a principled manner. Experimental results on synthetic and real-world data sets demonstrate the efficacy of the proposed methods.