Investor sentiment and machine learning : Predicting the price of China's crude oil futures market

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

1 Scopus Citations
View graph of relations


Related Research Unit(s)


Original languageEnglish
Article number123471
Journal / PublicationEnergy
Online published14 Feb 2022
Publication statusPublished - 15 May 2022


Sentiment analysis technology has made it possible to precisely calculate the daily reactions and opinions of investors, which has been found to have a significant influence on financial asset pricing. Thus, in this study, we examine the impacts that predictive power investor sentiment has over the price of China's crude oil. We first constructed investor sentiment indexes of China's crude oil futures based on specific economic variables and comments found on one of the most active online financial forums. Then, five popular machine learning tools were utilized to generate predictions. According to our findings, the long short-term memory model combined with the composite sentiment index performed the best due to a lower rate of prediction errors and greater directional accuracy for time-series forecasting of one-day-ahead prices. In this way, this study could aid researchers to more effectively investigate the energy sector which is rapidly changing and highly speculative in nature

Research Area(s)

  • Crude oil futures, Investor sentiment, Machine learning, Prediction