A Crude Oil Spot Price Forecasting Method Incorporating Quadratic Decomposition and Residual Forecasting
The world economy is affected by fluctuations in the price of crude oil, making precise and effective forecasting of crude oil prices essential. In this study, we propose a combined forecasting scheme, which combines a quadratic decomposition and optimized support vector regression (SVR). In the dec...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-01-01
|
| Series: | Journal of Mathematics |
| Online Access: | http://dx.doi.org/10.1155/2024/6652218 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832559313766318080 |
|---|---|
| author | Yonghui Duan Ziru Ming Xiang Wang |
| author_facet | Yonghui Duan Ziru Ming Xiang Wang |
| author_sort | Yonghui Duan |
| collection | DOAJ |
| description | The world economy is affected by fluctuations in the price of crude oil, making precise and effective forecasting of crude oil prices essential. In this study, we propose a combined forecasting scheme, which combines a quadratic decomposition and optimized support vector regression (SVR). In the decomposition part, the original crude oil price series are first decomposed using empirical modal decomposition (CEEMDAN), and then the residuals of the first decomposition (RES) are decomposed using variational modal decomposition (VMD). Additionally, this work proposes to optimize the support vector regression model (SVR) by the seagull optimization algorithm (SOA). Ultimately, the empirical investigation created the feature-variable system and predicted the filtered features. By computing evaluation indices like MAE, MSE, R2, and MAPE and validating using Brent and WTI crude oil spot, the prediction errors of the CEEMDAN -RES.-VMD -SOA-SVR combination prediction model presented in this paper are assessed and compared with those of the other twelve comparative models. The empirical evidence shows that the combination model being proposed in this paper outperforms the other related comparative models and improves the accuracy of the crude oil price forecasting model. |
| format | Article |
| id | doaj-art-d81a6cf45640417f94a44d3a2fc3b679 |
| institution | Kabale University |
| issn | 2314-4785 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Mathematics |
| spelling | doaj-art-d81a6cf45640417f94a44d3a2fc3b6792025-02-03T01:30:21ZengWileyJournal of Mathematics2314-47852024-01-01202410.1155/2024/6652218A Crude Oil Spot Price Forecasting Method Incorporating Quadratic Decomposition and Residual ForecastingYonghui Duan0Ziru Ming1Xiang Wang2Department of Civil EngineeringDepartment of Civil EngineeringDepartment of Civil EngineeringThe world economy is affected by fluctuations in the price of crude oil, making precise and effective forecasting of crude oil prices essential. In this study, we propose a combined forecasting scheme, which combines a quadratic decomposition and optimized support vector regression (SVR). In the decomposition part, the original crude oil price series are first decomposed using empirical modal decomposition (CEEMDAN), and then the residuals of the first decomposition (RES) are decomposed using variational modal decomposition (VMD). Additionally, this work proposes to optimize the support vector regression model (SVR) by the seagull optimization algorithm (SOA). Ultimately, the empirical investigation created the feature-variable system and predicted the filtered features. By computing evaluation indices like MAE, MSE, R2, and MAPE and validating using Brent and WTI crude oil spot, the prediction errors of the CEEMDAN -RES.-VMD -SOA-SVR combination prediction model presented in this paper are assessed and compared with those of the other twelve comparative models. The empirical evidence shows that the combination model being proposed in this paper outperforms the other related comparative models and improves the accuracy of the crude oil price forecasting model.http://dx.doi.org/10.1155/2024/6652218 |
| spellingShingle | Yonghui Duan Ziru Ming Xiang Wang A Crude Oil Spot Price Forecasting Method Incorporating Quadratic Decomposition and Residual Forecasting Journal of Mathematics |
| title | A Crude Oil Spot Price Forecasting Method Incorporating Quadratic Decomposition and Residual Forecasting |
| title_full | A Crude Oil Spot Price Forecasting Method Incorporating Quadratic Decomposition and Residual Forecasting |
| title_fullStr | A Crude Oil Spot Price Forecasting Method Incorporating Quadratic Decomposition and Residual Forecasting |
| title_full_unstemmed | A Crude Oil Spot Price Forecasting Method Incorporating Quadratic Decomposition and Residual Forecasting |
| title_short | A Crude Oil Spot Price Forecasting Method Incorporating Quadratic Decomposition and Residual Forecasting |
| title_sort | crude oil spot price forecasting method incorporating quadratic decomposition and residual forecasting |
| url | http://dx.doi.org/10.1155/2024/6652218 |
| work_keys_str_mv | AT yonghuiduan acrudeoilspotpriceforecastingmethodincorporatingquadraticdecompositionandresidualforecasting AT ziruming acrudeoilspotpriceforecastingmethodincorporatingquadraticdecompositionandresidualforecasting AT xiangwang acrudeoilspotpriceforecastingmethodincorporatingquadraticdecompositionandresidualforecasting AT yonghuiduan crudeoilspotpriceforecastingmethodincorporatingquadraticdecompositionandresidualforecasting AT ziruming crudeoilspotpriceforecastingmethodincorporatingquadraticdecompositionandresidualforecasting AT xiangwang crudeoilspotpriceforecastingmethodincorporatingquadraticdecompositionandresidualforecasting |