Volatility forecasting of crude oil futures based on a genetic algorithm regularization online extreme learning machine with a forgetting factor: The role of news during the COVID-19 pandemic. (October 2021)

• Record Type: Journal Article
• Authors: Weng, Futian; Zhang, Hongwei; Yang, Cai
• Is Part Of: Resources policy. Volume 73(2021)
• Publication Date: 2021-10
• Subjects: COVID-19 -- Crude oil -- Genetic algorithm -- OS-ELM -- Volatility forecasting; Mines and mineral resources -- Periodicals; Ressources minérales -- Périodiques; Ressources naturelles -- Gestion -- Périodiques; Environnement -- Politique gouvernementale -- Périodiques; 333.8
• DOI: 10.1016/j.resourpol.2021.102148
• Languages: English
• ISSNs: 0301-4207

Abstract

Abstract: The outbreak of news and opinions during the COVID-19 pandemic is unprecedented in this age of rapid dissemination of information. The ensuing uncertainty has led to the emergence of heightened volatility in prices of crude oil futures. Whether such news has predictive value for the volatility of crude oil futures during the COVID-19 pandemic is examined in this research. We proposed a modeling framework, genetic algorithm regularization online extreme learning machine with forgetting factor (GA-RFOS-ELM), to estimate the effects of news during the COVID-19 pandemic on the volatility of crude oil futures. GA-RFOS-ELM could learn block-by-block with fixed or varying block size when considering the block own valid period. The experimental results illustrate that news during the COVID-19 pandemic has more predictive information, which is crucial for short-term volatility forecasting of crude oil futures. The novel approach illustrates that online update learning ability is needed during the COVID-19 pandemic, which could be effective and efficient in volatility forecasting of crude oil futures. The contributions of our study are significant for investors and administrators to predict and understand the behavior of volatility during the COVID-19 pandemic. Highlights: News during the COVID-19 pandemic is crucial for the volatility forecasting of crude oil futures. A GA-RFOS-ELM model considering the timeliness aspect of news and generalization ability is developed. Volatility forecasting during the COVID-19 pandemic is more precise when considering the COVID-19-related news. Online update learning ability is needed for volatility forecasting during the COVID-19 pandemic.