Hybrid Deep Learning for Gas Price Prediction Using Multi-Factor and Temporal Features
Natural gas prices are a vital indicator of a country’s economic conditions. Accurately forecasting natural gas prices is challenging due to the complex interaction of various factors. Traditional methods often consider linear factors or the impact of historical natural gas prices in isol...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10820508/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590341598871552 |
|---|---|
| author | Shuliang Zhang Hao Wu Jin Wang Longsheng Du |
| author_facet | Shuliang Zhang Hao Wu Jin Wang Longsheng Du |
| author_sort | Shuliang Zhang |
| collection | DOAJ |
| description | Natural gas prices are a vital indicator of a country’s economic conditions. Accurately forecasting natural gas prices is challenging due to the complex interaction of various factors. Traditional methods often consider linear factors or the impact of historical natural gas prices in isolation, failing to fully capture the intrinsic connections between these factors. In this paper, we innovatively apply k-means clustering to analyze the correlations of multiple factors affecting natural gas prices and design a hybrid deep learning model that integrates both multi-factor and time series features. Through experimental validation on three public datasets, our proposed model achieves industry-leading predictive performance with a mean squared absolute error of 2.27, which is approximately a 1/3 improvement over the current state-of-the-art methods. |
| format | Article |
| id | doaj-art-89e4020dd5254d719657570f57207a64 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-89e4020dd5254d719657570f57207a642025-01-24T00:01:56ZengIEEEIEEE Access2169-35362025-01-0113119891200110.1109/ACCESS.2024.352512810820508Hybrid Deep Learning for Gas Price Prediction Using Multi-Factor and Temporal FeaturesShuliang Zhang0https://orcid.org/0000-0003-0285-888XHao Wu1Jin Wang2Longsheng Du3School of Business, Linyi University, Linyi, ChinaSchool of Economics and Management, Zhejiang University of Science and Technology, Hangzhou, ChinaParty School of the Shantou Committee of C.P.C, Shantou, ChinaPetroChina Lubricant, Daqing Branch, Daqing, ChinaNatural gas prices are a vital indicator of a country’s economic conditions. Accurately forecasting natural gas prices is challenging due to the complex interaction of various factors. Traditional methods often consider linear factors or the impact of historical natural gas prices in isolation, failing to fully capture the intrinsic connections between these factors. In this paper, we innovatively apply k-means clustering to analyze the correlations of multiple factors affecting natural gas prices and design a hybrid deep learning model that integrates both multi-factor and time series features. Through experimental validation on three public datasets, our proposed model achieves industry-leading predictive performance with a mean squared absolute error of 2.27, which is approximately a 1/3 improvement over the current state-of-the-art methods.https://ieeexplore.ieee.org/document/10820508/Gas pricehybrid learningLSTMattention |
| spellingShingle | Shuliang Zhang Hao Wu Jin Wang Longsheng Du Hybrid Deep Learning for Gas Price Prediction Using Multi-Factor and Temporal Features IEEE Access Gas price hybrid learning LSTM attention |
| title | Hybrid Deep Learning for Gas Price Prediction Using Multi-Factor and Temporal Features |
| title_full | Hybrid Deep Learning for Gas Price Prediction Using Multi-Factor and Temporal Features |
| title_fullStr | Hybrid Deep Learning for Gas Price Prediction Using Multi-Factor and Temporal Features |
| title_full_unstemmed | Hybrid Deep Learning for Gas Price Prediction Using Multi-Factor and Temporal Features |
| title_short | Hybrid Deep Learning for Gas Price Prediction Using Multi-Factor and Temporal Features |
| title_sort | hybrid deep learning for gas price prediction using multi factor and temporal features |
| topic | Gas price hybrid learning LSTM attention |
| url | https://ieeexplore.ieee.org/document/10820508/ |
| work_keys_str_mv | AT shuliangzhang hybriddeeplearningforgaspricepredictionusingmultifactorandtemporalfeatures AT haowu hybriddeeplearningforgaspricepredictionusingmultifactorandtemporalfeatures AT jinwang hybriddeeplearningforgaspricepredictionusingmultifactorandtemporalfeatures AT longshengdu hybriddeeplearningforgaspricepredictionusingmultifactorandtemporalfeatures |