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

作者：Jiang, Zhe; Zhang, Lin; Zhang, Lingling; Wen, Bo^*

来源：Energy, 2022, 247: 123471.

DOI：10.1016/j.energy.2022.123471

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

Sentiment analysis technology has made it possible to precisely calculate the daily reactions and opin-ions 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.

• 单位
  中国科学院研究生院