Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/271249 
Year of Publication: 
2021
Series/Report no.: 
QMS Research Paper No. 2021/04
Publisher: 
Queen's University Belfast, Queen's Management School, Belfast
Abstract: 
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.
Subjects: 
Forecasting
Crude oil
Realized volatility
Exogenous predictors
Machine learning
JEL: 
C22
C45
E37
Q47
Persistent Identifier of the first edition: 
Document Type: 
Working Paper

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.