| Title | Sustainable supply chain decision-making in the automotive industry: A data-driven approach |
|---|---|
| ID_Doc | 73378 |
| Authors | Beinabadi, HZ; Baradaran, V; Komijan, AR |
| Title | Sustainable supply chain decision-making in the automotive industry: A data-driven approach |
| Year | 2024 |
| Published | |
| Abstract | The auto parts manufacturing sector faces multifaceted challenges ranging from production planning to sustainability imperatives, necessitating innovative solutions. This study presents an integrated data-driven approach tailored to address these challenges. Leveraging advanced AI techniques, including Convolutional and Recurrent Neural Networks optimized with the Moth-flame Optimization Algorithm (MFO), we accurately predict demand quantities for automotive components. Through empirical validation with Iranian auto parts manufacturers, our model achieves an impressive accuracy rate of over 90 %. Subsequently, Data Envelopment Analysis (DEA) evaluates suppliers not only based on demand quantities but also on their social, economic, and environmental impacts, with a resulting average efficiency score of 0.75. The Best-Worst Method (BWM) further refines supplier selection, leading to the identification of top-performing suppliers with an average score of 0.8. This comprehensive approach enables auto parts manufacturers to optimize production planning processes while aligning with sustainable development goals. The successful application of our model underscores the transformative potential of integrating business analytics and AI in the automotive industry towards sustainability. |
No similar articles found.