Optimizing Supply Chain Resilience Using Advanced Analytics and Computational Intelligence Techniques
This paper presents a novel resilient supply chain management (SCM) structure leveraging advanced artificial intelligence (AI) techniques, specifically Long Short-Term Memory (LSTM) networks and Particle Swarm Optimization (PSO). The primary objective is to enhance supply chain efficiency and robust...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10817559/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576798162944000 |
|---|---|
| author | Jie Xu Lixing Bo |
| author_facet | Jie Xu Lixing Bo |
| author_sort | Jie Xu |
| collection | DOAJ |
| description | This paper presents a novel resilient supply chain management (SCM) structure leveraging advanced artificial intelligence (AI) techniques, specifically Long Short-Term Memory (LSTM) networks and Particle Swarm Optimization (PSO). The primary objective is to enhance supply chain efficiency and robustness by integrating these AI methods to address common challenges such as demand forecasting, resource allocation, and cost reduction. The proposed methodology combines LSTM for accurate demand forecasting with PSO for optimizing resource allocation and cost management. LSTM’s strength in capturing complex temporal patterns is utilized to predict demand with high precision, while PSO is employed to optimize various supply chain components, including inventory management, transportation, and production planning. The system’s effectiveness is evaluated through extensive experimentation and case studies, focusing on metrics such as forecasting accuracy, cost reduction, and resource utilization. Key findings indicate that the integrated LSTM-PSO system significantly outperforms traditional SCM methods. It achieves a 12% reduction in overall SCM costs, improves demand forecasting accuracy with reduced mean absolute error (MAE) and root mean squared error (RMSE), and enhances resource utilization efficiency by up to 20%. Additionally, the system demonstrates notable improvements in operational efficiency, with increased system uptime and reduced order error rates. The implications of this research are substantial; it provides a comprehensive framework that combines predictive and optimization capabilities, offering a robust solution to contemporary SCM challenges. By integrating LSTM and PSO, the research advances the field toward achieving resilient and efficient supply chain operations, with practical implications for enhancing overall performance and reducing costs in complex supply chain environments. |
| format | Article |
| id | doaj-art-f5f4060fcb5c422e9782a50065c3e9fb |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-f5f4060fcb5c422e9782a50065c3e9fb2025-01-31T00:01:34ZengIEEEIEEE Access2169-35362025-01-0113180631807810.1109/ACCESS.2024.352347010817559Optimizing Supply Chain Resilience Using Advanced Analytics and Computational Intelligence TechniquesJie Xu0https://orcid.org/0009-0001-6611-1550Lixing Bo1School of Finance and Tourism, Chongqing Vocational Institute of Engineering, Chongqing, ChinaSchool of Management, Universiti Sains Malaysia, Pulau, Penang, MalaysiaThis paper presents a novel resilient supply chain management (SCM) structure leveraging advanced artificial intelligence (AI) techniques, specifically Long Short-Term Memory (LSTM) networks and Particle Swarm Optimization (PSO). The primary objective is to enhance supply chain efficiency and robustness by integrating these AI methods to address common challenges such as demand forecasting, resource allocation, and cost reduction. The proposed methodology combines LSTM for accurate demand forecasting with PSO for optimizing resource allocation and cost management. LSTM’s strength in capturing complex temporal patterns is utilized to predict demand with high precision, while PSO is employed to optimize various supply chain components, including inventory management, transportation, and production planning. The system’s effectiveness is evaluated through extensive experimentation and case studies, focusing on metrics such as forecasting accuracy, cost reduction, and resource utilization. Key findings indicate that the integrated LSTM-PSO system significantly outperforms traditional SCM methods. It achieves a 12% reduction in overall SCM costs, improves demand forecasting accuracy with reduced mean absolute error (MAE) and root mean squared error (RMSE), and enhances resource utilization efficiency by up to 20%. Additionally, the system demonstrates notable improvements in operational efficiency, with increased system uptime and reduced order error rates. The implications of this research are substantial; it provides a comprehensive framework that combines predictive and optimization capabilities, offering a robust solution to contemporary SCM challenges. By integrating LSTM and PSO, the research advances the field toward achieving resilient and efficient supply chain operations, with practical implications for enhancing overall performance and reducing costs in complex supply chain environments.https://ieeexplore.ieee.org/document/10817559/Supply chain management (SCM)long short-term memory (LSTM)particle swarm optimization (PSO)demand forecastingresource allocation |
| spellingShingle | Jie Xu Lixing Bo Optimizing Supply Chain Resilience Using Advanced Analytics and Computational Intelligence Techniques IEEE Access Supply chain management (SCM) long short-term memory (LSTM) particle swarm optimization (PSO) demand forecasting resource allocation |
| title | Optimizing Supply Chain Resilience Using Advanced Analytics and Computational Intelligence Techniques |
| title_full | Optimizing Supply Chain Resilience Using Advanced Analytics and Computational Intelligence Techniques |
| title_fullStr | Optimizing Supply Chain Resilience Using Advanced Analytics and Computational Intelligence Techniques |
| title_full_unstemmed | Optimizing Supply Chain Resilience Using Advanced Analytics and Computational Intelligence Techniques |
| title_short | Optimizing Supply Chain Resilience Using Advanced Analytics and Computational Intelligence Techniques |
| title_sort | optimizing supply chain resilience using advanced analytics and computational intelligence techniques |
| topic | Supply chain management (SCM) long short-term memory (LSTM) particle swarm optimization (PSO) demand forecasting resource allocation |
| url | https://ieeexplore.ieee.org/document/10817559/ |
| work_keys_str_mv | AT jiexu optimizingsupplychainresilienceusingadvancedanalyticsandcomputationalintelligencetechniques AT lixingbo optimizingsupplychainresilienceusingadvancedanalyticsandcomputationalintelligencetechniques |