Crude oil price forecasting based on internet concern using an extreme learning machine

Jue Wang, George Athanasopoulos, Rob J. Hyndman, Shouyang Wang

Research output: Contribution to journalArticleResearchpeer-review

98 Citations (Scopus)


The growing internet concern (IC) over the crude oil market and related events influences market trading, thus creating further instability within the oil market itself. We propose a modeling framework for analyzing the effects of IC on the oil market and for predicting the price volatility of crude oil's futures market. This novel approach decomposes the original time series into intrinsic modes at different time scales using bivariate empirical mode decomposition (BEMD). The relationship between the oil price volatility and IC at an individual frequency is investigated. By utilizing decomposed intrinsic modes as specified characteristics, we also construct extreme learning machine (ELM) models with variant forecasting schemes. The experimental results illustrate that ELM models that incorporate intrinsic modes and IC outperform the baseline ELM and other benchmarks at distinct horizons. Having the power to improve the accuracy of baseline models, internet searching is a practical way of quantifying investor attention, which can help to predict short-run price fluctuations in the oil market.

Original languageEnglish
Pages (from-to)665-677
Number of pages13
JournalInternational Journal of Forecasting
Issue number4
Publication statusPublished - 1 Oct 2018


  • BEMD
  • Crude oil futures price
  • ELM
  • Internet concern

Cite this