Enhanced futures price-spread forecasting based on an attention-driven optimized LSTM network: integrating an improved grey wolf optimizer algorithm for enhanced accuracy
Financial market prediction faces significant challenges due to the complex temporal dependencies and heterogeneous data relationships inherent in futures price-spread data. Traditional machine learning methods struggle to effectively mine these patterns, while conventional long short-term memory (L...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2025-06-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-2865.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850122912688766976 |
|---|---|
| author | Yongli Tang Zhenlun Gao Zhongqi Cai Jinxia Yu Panke Qin |
| author_facet | Yongli Tang Zhenlun Gao Zhongqi Cai Jinxia Yu Panke Qin |
| author_sort | Yongli Tang |
| collection | DOAJ |
| description | Financial market prediction faces significant challenges due to the complex temporal dependencies and heterogeneous data relationships inherent in futures price-spread data. Traditional machine learning methods struggle to effectively mine these patterns, while conventional long short-term memory (LSTM) models lack focused feature prioritization and suffer from suboptimal hyperparameter selection. This article proposes the Improved Grey Wolf Optimizer with Multi-headed Self-attention and LSTM (IGML) model, which integrates a multi-head self-attention mechanism to enhance feature interaction and introduces an improved grey wolf optimizer (IGWO) with four strategic enhancements for automated hyperparameter tuning. Benchmark tests on optimization problems validate IGWO’s superior convergence efficiency. Evaluated on real futures price-spread datasets, the IGML reduces mean square error (RMSE) and mean absolute error (MAE) by up to 88% and 85%, respectively, compared to baseline models, demonstrating its practical efficacy in capturing intricate financial market dynamics. |
| format | Article |
| id | doaj-art-3ea4c8fc1df04d8db371ca1ffd36cef9 |
| institution | OA Journals |
| issn | 2376-5992 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj-art-3ea4c8fc1df04d8db371ca1ffd36cef92025-08-20T02:34:43ZengPeerJ Inc.PeerJ Computer Science2376-59922025-06-0111e286510.7717/peerj-cs.2865Enhanced futures price-spread forecasting based on an attention-driven optimized LSTM network: integrating an improved grey wolf optimizer algorithm for enhanced accuracyYongli Tang0Zhenlun Gao1Zhongqi Cai2Jinxia Yu3Panke Qin4School of Software, Henan Polytechnic University, Jiaozuo, Henan, ChinaSchool of Software, Henan Polytechnic University, Jiaozuo, Henan, ChinaSchool of Software, Henan Polytechnic University, Jiaozuo, Henan, ChinaSchool of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, Henan, ChinaSchool of Software, Henan Polytechnic University, Jiaozuo, Henan, ChinaFinancial market prediction faces significant challenges due to the complex temporal dependencies and heterogeneous data relationships inherent in futures price-spread data. Traditional machine learning methods struggle to effectively mine these patterns, while conventional long short-term memory (LSTM) models lack focused feature prioritization and suffer from suboptimal hyperparameter selection. This article proposes the Improved Grey Wolf Optimizer with Multi-headed Self-attention and LSTM (IGML) model, which integrates a multi-head self-attention mechanism to enhance feature interaction and introduces an improved grey wolf optimizer (IGWO) with four strategic enhancements for automated hyperparameter tuning. Benchmark tests on optimization problems validate IGWO’s superior convergence efficiency. Evaluated on real futures price-spread datasets, the IGML reduces mean square error (RMSE) and mean absolute error (MAE) by up to 88% and 85%, respectively, compared to baseline models, demonstrating its practical efficacy in capturing intricate financial market dynamics.https://peerj.com/articles/cs-2865.pdfFutures price-spread forecastingLSTM networkHyperparameter optimizationAttention mechanism |
| spellingShingle | Yongli Tang Zhenlun Gao Zhongqi Cai Jinxia Yu Panke Qin Enhanced futures price-spread forecasting based on an attention-driven optimized LSTM network: integrating an improved grey wolf optimizer algorithm for enhanced accuracy PeerJ Computer Science Futures price-spread forecasting LSTM network Hyperparameter optimization Attention mechanism |
| title | Enhanced futures price-spread forecasting based on an attention-driven optimized LSTM network: integrating an improved grey wolf optimizer algorithm for enhanced accuracy |
| title_full | Enhanced futures price-spread forecasting based on an attention-driven optimized LSTM network: integrating an improved grey wolf optimizer algorithm for enhanced accuracy |
| title_fullStr | Enhanced futures price-spread forecasting based on an attention-driven optimized LSTM network: integrating an improved grey wolf optimizer algorithm for enhanced accuracy |
| title_full_unstemmed | Enhanced futures price-spread forecasting based on an attention-driven optimized LSTM network: integrating an improved grey wolf optimizer algorithm for enhanced accuracy |
| title_short | Enhanced futures price-spread forecasting based on an attention-driven optimized LSTM network: integrating an improved grey wolf optimizer algorithm for enhanced accuracy |
| title_sort | enhanced futures price spread forecasting based on an attention driven optimized lstm network integrating an improved grey wolf optimizer algorithm for enhanced accuracy |
| topic | Futures price-spread forecasting LSTM network Hyperparameter optimization Attention mechanism |
| url | https://peerj.com/articles/cs-2865.pdf |
| work_keys_str_mv | AT yonglitang enhancedfuturespricespreadforecastingbasedonanattentiondrivenoptimizedlstmnetworkintegratinganimprovedgreywolfoptimizeralgorithmforenhancedaccuracy AT zhenlungao enhancedfuturespricespreadforecastingbasedonanattentiondrivenoptimizedlstmnetworkintegratinganimprovedgreywolfoptimizeralgorithmforenhancedaccuracy AT zhongqicai enhancedfuturespricespreadforecastingbasedonanattentiondrivenoptimizedlstmnetworkintegratinganimprovedgreywolfoptimizeralgorithmforenhancedaccuracy AT jinxiayu enhancedfuturespricespreadforecastingbasedonanattentiondrivenoptimizedlstmnetworkintegratinganimprovedgreywolfoptimizeralgorithmforenhancedaccuracy AT pankeqin enhancedfuturespricespreadforecastingbasedonanattentiondrivenoptimizedlstmnetworkintegratinganimprovedgreywolfoptimizeralgorithmforenhancedaccuracy |