Interval Forecasts for Gas Prices in the Face of Structural Breaks -- Statistical Models vs. Neural Networks

TL;DR

This study compares statistical and neural network models for gas price interval forecasting, especially during structural shocks like the Ukraine war, highlighting their resilience and performance in volatile periods.

Contribution

It provides an empirical comparison of traditional statistical models and neural networks in gas price interval forecasting amid structural breaks.

Findings

Statistical and neural network models underestimate variance during shocks.

Simpler models perform best during shock periods for interval coverage.

Long-short term neural networks are outperformed by other models.

Abstract

Reliable gas price forecasts are an essential information for gas and energy traders, for risk managers and also economists. However, ahead of the war in Ukraine Europe began to suffer from substantially increased and volatile gas prices which culminated in the aftermath of the North Stream 1 explosion. This shock changed both trend and volatility structure of the prices and has considerable effects on forecasting models. In this study we investigate whether modern machine learning methods such as neural networks are more resilient against such changes than statistical models such as autoregressive moving average (ARMA) models with conditional heteroskedasticity, or copula-based time series models. Thereby the focus lies on interval forecasting and applying respective evaluation measures. As data, the Front Month prices from the Dutch Title Transfer Facility, currently the predominant European exchange, are used. We see that, during the shock period, most models underestimate the variance while overestimating the variance in the after-shock period. Furthermore, we recognize that, during the shock, the simpler models, i.e. an ARMA model with conditional heteroskedasticity and the multilayer perceptron (a neural network), perform best with regards to prediction interval coverage. Interestingly, the widely-used long-short term neural network is outperformed by its competitors.