Forecasting realized volatility of crude oil futures prices based on machine learning

Research output: Contribution to journalResearch articleContributedpeer-review

Contributors

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 that are constructed with these forecasts outperform their competing models 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.

Details

Original languageEnglish
Pages (from-to)1422-1446
Number of pages25
JournalJournal of Forecasting
Volume43
Issue number5
Early online date2024
Publication statusPublished - Aug 2024
Peer-reviewedYes

External IDs

ORCID /0000-0003-4359-987X/work/154193050
Scopus 85185664082
Mendeley 17e195ad-5ba2-38b0-8fb7-e70bf01dc584

Keywords

Keywords

  • exogenous predictors, crude oil, forecasting, realized volatility, machine learning