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!
|
| Summary: | 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. |
|---|---|
| ISSN: | 2169-3536 |