Optimized Supply Chain Process by Advanced Analytics and Machine Learnings
Increased complexity and dynamism in global supply chains have necessitated the adoption of advanced analytics and machine learning (ML) techniques to achieve optimum efficiency, lower costs, and enhance operational resilience. This study provides a comprehensive literature review of the application of ML in supply chain management (SCM), such as demand forecasting, inventory optimization, logistics planning, and delivery efficiency. By synthesizing results from various case studies, including Walmart's inventory management using AI, e-commerce logistics optimization using CatBoost, and Rossmann Stores' demand forecasting using Gated Recurrent Units (GRUs). This research investigates the comparative effectiveness of various ML models in solving key SCM problems. Findings highlight the superiority of ML techniques over traditional SCM approaches, particularly in predictive analytics and decision automation. Random Forest algorithms have demonstrated exceptional performance in demand forecasting by capturing non-linear relationships in sales trends, while CatBoost has shown remarkable efficiency in handling categorical data for logistics planning. Deep learning models, such as GRUs, have improved time-series forecasting accuracy by incorporating external factors like weather conditions and economic indicators. Furthermore, AI-driven inventory management has been instrumental in reducing costs, increasing turnover rates, minimizing stockouts, and ensuring optimized warehouse operations. This study also identifies key challenges associated with ML adoption in SCM, including data integration issues, computational complexity, model interpretability, and resistance to change within organizations. Despite these limitations, the potential of ML in revolutionizing supply chains is immense, offering enhanced scalability, adaptability, and sustainability. The research emphasizes the need for businesses to develop structured frameworks for AI-driven SCM implementation, incorporating sustainability metrics to ensure long-term resilience and environmental responsibility. The insights derived from this literature review contribute to the growing body of knowledge on AI-powered supply chain optimization, providing actionable recommendations for industry practitioners. As businesses continue to navigate supply chain disruptions and evolving market demands, the adoption of ML-based predictive analytics will be crucial in maintaining competitive advantage and operational agility in the modern marketplace.
Files
Metadata
| Work Title | Optimized Supply Chain Process by Advanced Analytics and Machine Learnings |
|---|---|
| Access | |
| Creators |
|
| Keyword |
|
| License | CC BY-ND 4.0 (Attribution-NoDerivatives) |
| Work Type | Masters Culminating Experience |
| Sub Work Type | Scholarly Paper/Essay (MA/MS) |
| Program | Information Systems |
| Degree | Master of Science |
| Acknowledgments |
|
| Publisher |
|
| Publication Date | April 2025 |
| DOI | doi:10.26207/j4q8-2761 |
| Deposited | April 23, 2025 |
Versions
Analytics
Collections
This resource is currently not in any collection.