Forecasting Natural Gas Prices with Spatio-Temporal Copula-based Time Series Models

Abstract

Commodity price time series possess interesting features, such as heavy-tailedness, skewness, heteroskedasticity, and non-linear dependence structures. These features pose challenges for modeling and forecasting. In this work, we explore how spatio-temporal copula-based time series models can be effectively employed for these purposes. We focus on price series for fossil fuels and carbon emissions. Further, we illustrate how the t-copula may be used in conditional heteroskedasticity modeling. The possible emergence of non-elliptical probabilistic forecasts in this context is examined and visualized. The problem of finding an appropriate point forecast given a non-elliptical probabilistic forecast is discussed. We propose a solution where the forecast is augmented with an artificial neural network (ANN). The ANN predicts the best (in MSE sense) quantile to use as point forecast. In a forecasting study, we find that the copula-based models are competitive.