Forecasting oil prices volatility with Google searches
Predikce volatility cen ropy pomocí Google Trends
bachelor thesis (DEFENDED)
View/ Open
Permanent link
http://hdl.handle.net/20.500.11956/109576Identifiers
Study Information System: 191687
Collections
- Kvalifikační práce [17123]
Author
Advisor
Referee
Zafeiris, Dimitrios
Faculty / Institute
Faculty of Social Sciences
Discipline
Economics and Finance
Department
Institute of Economic Studies
Date of defense
10. 9. 2019
Publisher
Univerzita Karlova, Fakulta sociálních vědLanguage
English
Grade
Very good
Keywords (Czech)
Google Trends, ropa, VAR, vyhledávací dotaz, volatilita, nowcastingKeywords (English)
Google Trends, oil, VAR, search query, price volatility, nowcastingKombinácia zrýchlujucej sa dynamiky obchodovania na trhu s ropou a rapídneho rozvoja technológií umožňuje jednoduchý prenos externých informačných šokov cez internet. V tejto práci skúmame vzájomné vzťahy medzi troma referenčnými cenami ropy, CBOE Cruide oil indexom volatility a Google vyhľadávaniami. Za účelom testovania Grangerovej kauzality a uskutučnenia impulse-response analýzy sme vytvorili VAR model. Výsledky ukazujú jednostranné aj obojstranný pričinný vzťah medzi cenami ropy, OVX a Google vyhľadávaniami. Out-of sample predpovede a Diebold-Marianov test nám ukázali je možné využiť Google trends na zlepšenie krátkodobej predikciu v prípade modelu s WTI cenami a indexom volatility.
Oil market pricing is highly susceptible to geopolitical and economic events. With the rapid development of information technology, energy market can quickly get external information shocks through the Internet. This thesis examines the relationship between prices of three oil benchmarks, CBOE Crude Oil Volatility Index, and Google search queries. We built VAR model to study Granger causality and to provide impulse response analysis. Results indicate both one side and two-side causal relationship between oil-related series and most of the search queries. Out-of sample forecasting with measures of predictive accuracy and Diebold-Mariano test demonstrated that Google trends can improve short-run prediction potential only for models with WTI price and volatility index.