Coupling High-Frequency Data with Nonlinear Models in Multiple-Step-Ahead Forecasting of Energy Markets' Volatility

Abstract

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Abstract: Terms of use: Documents inIn the past decade, the popularity of realized measures and various linear models for volatility forecasting has attracted attention in the literature on the price variability of energy markets. However, results that would guide practitioners to a specifc estimator and model when aiming for the best forecasting accuracy are missing. This paper contributes to the ongoing debate with a comprehensive evaluation of multiple-step-ahead volatility forecasts of energy markets using several popular high-frequency measures and forecasting models. To capture the complex patterns hidden to linear models commonly used to forecast realized volatility, this paper also contributes to the literature by coupling realized measures with artificial neural networks as a forecasting tool. Forecasting performance is compared across models as well as realized measures of crude oil, heating oil, and natural gas volatility during three qualitatively distinct periods covering the precrisis period, recent global turmoil of markets in 2008, and the most recent post-crisis period. We conclude that coupling realized measures with arti_cial neural networks results in both statistical and economic gains, reducing the tendency to over-predict volatility uniformly during all tested periods. Our analysis favors the median realized volatility, as it delivers the best performance and is a computationally simple alternative for practitioners.

Forecasting the Term Structure of Crude Oil Futures Prices with Neural Networks

“…While asymmetric errors are commonly found by the volatility literature, it may be also of interest to see if the models do not over-, or under-predict the term structures systematically. For example Nomikos and Pouliasis (2011); Wang and Wu (2012); Baruník and Křehlík (2014) find majority of forecasting models to over-predict the volatility on petroleum markets. The bias then translates to direct economic losses.…”

“…Whereas the number of models using machine learning is rapidly growing in the academic literature, applications in energy markets are very limited. While several works use neural networks in energy forecasting (Fan et al, 2008;Yu et al, 2008;Xiong et al, 2013;Jammazi and Aloui, 2012;Papadimitriou et al, 2014;Baruník and Křehlík, 2014), we are the first to employ the approach in forecasting of term structures.…”