Crude oil price prediction using CEEMDAN and LSTM-attention with news sentiment index

Crude oil is one of the most powerful types of energy and the fluctuation of its price influences the global economy. Therefore, building a scientific model to accurately predict the price of crude oil is significant for investors, governments and researchers. However, the nonlinearity and nonstatio...

Full description

Bibliographic Details
Main Author: Hu Zhenda
Format: Article
Language:English
Published: EDP Sciences 2021-01-01
Series:Oil & Gas Science and Technology
Online Access:https://ogst.ifpenergiesnouvelles.fr/articles/ogst/full_html/2021/01/ogst200291/ogst200291.html
id doaj-61c7b7cbdde34d91874d5281817226b0
record_format Article
spelling doaj-61c7b7cbdde34d91874d5281817226b02021-05-04T12:23:05ZengEDP SciencesOil & Gas Science and Technology1294-44751953-81892021-01-01762810.2516/ogst/2021010ogst200291Crude oil price prediction using CEEMDAN and LSTM-attention with news sentiment indexHu Zhendahttps://orcid.org/0000-0002-9450-5645Crude oil is one of the most powerful types of energy and the fluctuation of its price influences the global economy. Therefore, building a scientific model to accurately predict the price of crude oil is significant for investors, governments and researchers. However, the nonlinearity and nonstationarity of crude oil prices make it a challenging task for forecasting time series accurately. To handle the issue, this paper proposed a novel forecasting approach for crude oil prices that combines Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Long Short-Term Memory (LSTM) with attention mechanism and addition, following the well-known “decomposition and ensemble” framework. In addition, a news sentiment index based on Chinese crude oil news texts was constructed and added to the prediction of crude oil prices. And we made full use of attention mechanism to better integrate price series and sentiment series according to the characteristics of each component. To validate the performance of the proposed CEEMDAN-LSTM_att-ADD, we selected the Mean Absolute Percent Error (MAPE), the Root Mean Squared Error (RMSE) and the Diebold-Mariano (DM) statistic as evaluation criterias. Abundant experiments were conducted on West Texas Intermediate (WTI) spot crude oil prices. The proposed approach outperformed several state-of-the-art methods for forecasting crude oil prices, which proved the effectiveness of the CEEMDAN-LSTM_att-ADD with the news sentiment index.https://ogst.ifpenergiesnouvelles.fr/articles/ogst/full_html/2021/01/ogst200291/ogst200291.html
collection DOAJ
language English
format Article
sources DOAJ
author Hu Zhenda
spellingShingle Hu Zhenda
Crude oil price prediction using CEEMDAN and LSTM-attention with news sentiment index
Oil & Gas Science and Technology
author_facet Hu Zhenda
author_sort Hu Zhenda
title Crude oil price prediction using CEEMDAN and LSTM-attention with news sentiment index
title_short Crude oil price prediction using CEEMDAN and LSTM-attention with news sentiment index
title_full Crude oil price prediction using CEEMDAN and LSTM-attention with news sentiment index
title_fullStr Crude oil price prediction using CEEMDAN and LSTM-attention with news sentiment index
title_full_unstemmed Crude oil price prediction using CEEMDAN and LSTM-attention with news sentiment index
title_sort crude oil price prediction using ceemdan and lstm-attention with news sentiment index
publisher EDP Sciences
series Oil & Gas Science and Technology
issn 1294-4475
1953-8189
publishDate 2021-01-01
description Crude oil is one of the most powerful types of energy and the fluctuation of its price influences the global economy. Therefore, building a scientific model to accurately predict the price of crude oil is significant for investors, governments and researchers. However, the nonlinearity and nonstationarity of crude oil prices make it a challenging task for forecasting time series accurately. To handle the issue, this paper proposed a novel forecasting approach for crude oil prices that combines Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Long Short-Term Memory (LSTM) with attention mechanism and addition, following the well-known “decomposition and ensemble” framework. In addition, a news sentiment index based on Chinese crude oil news texts was constructed and added to the prediction of crude oil prices. And we made full use of attention mechanism to better integrate price series and sentiment series according to the characteristics of each component. To validate the performance of the proposed CEEMDAN-LSTM_att-ADD, we selected the Mean Absolute Percent Error (MAPE), the Root Mean Squared Error (RMSE) and the Diebold-Mariano (DM) statistic as evaluation criterias. Abundant experiments were conducted on West Texas Intermediate (WTI) spot crude oil prices. The proposed approach outperformed several state-of-the-art methods for forecasting crude oil prices, which proved the effectiveness of the CEEMDAN-LSTM_att-ADD with the news sentiment index.
url https://ogst.ifpenergiesnouvelles.fr/articles/ogst/full_html/2021/01/ogst200291/ogst200291.html
work_keys_str_mv AT huzhenda crudeoilpricepredictionusingceemdanandlstmattentionwithnewssentimentindex
_version_ 1721478970875052032