Arbeitspapier

Forecasting Realized Volatility of Crude Oil Futures Prices based on Machine Learning

Extending the popular HAR model with additional information channels to forecast realized volatility of WTI futures prices, we show that machine learning generated forecasts provide better forecasting quality and that portfolios which are constructed with these forecasts outperform their competing models and resulting in economic gains. Analyzing the selection process, we show that information channels vary across forecasting horizon. Variable selection produces clusters and provides evidence that there are structural changes with regard to the significance of information channels.

Sprache
Englisch

Erschienen in
Series: QMS Research Paper ; No. 2021/04

Klassifikation
Wirtschaft
Single Equation Models; Single Variables: Time-Series Models; Dynamic Quantile Regressions; Dynamic Treatment Effect Models; Diffusion Processes
Neural Networks and Related Topics
Prices, Business Fluctuations, and Cycles: Forecasting and Simulation: Models and Applications
Energy Forecasting
Thema
Forecasting
Crude oil
Realized volatility
Exogenous predictors
Machine learning

Ereignis
Geistige Schöpfung
(wer)
Luo, Jiawen
Klein, Tony
Walther, Thomas
Ji, Qiang
Ereignis
Veröffentlichung
(wer)
Queen's University Belfast, Queen's Management School
(wo)
Belfast
(wann)
2021

DOI
doi:10.2139/ssrn.3701000
Handle
Letzte Aktualisierung
10.03.2025, 11:45 MEZ

Datenpartner

Dieses Objekt wird bereitgestellt von:
ZBW - Deutsche Zentralbibliothek für Wirtschaftswissenschaften - Leibniz-Informationszentrum Wirtschaft. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.

Objekttyp

  • Arbeitspapier

Beteiligte

  • Luo, Jiawen
  • Klein, Tony
  • Walther, Thomas
  • Ji, Qiang
  • Queen's University Belfast, Queen's Management School

Entstanden

  • 2021

Ähnliche Objekte (12)