<![CDATA[Rising supply chain disruptions highlight increasing vulnerabilities in global logistics networks caused by geopolitical conflicts, fluctuating demand, transportation failures, and environmental instability. These challenges reveal the limitations of conventional risk assessment approaches that rely heavily on manual analysis and historical data. Machine Learning (ML) offers a promising approach to enhance predictive intelligence and support more accurate decision making in complex supply chain environments. This study aims to develop and evaluate a Machine Learning based risk prediction model capable of identifying potential supply chain disruptions and enabling early detection of critical risk factors in global logistics operations. A quantitative experimental approach was employed using supply chain datasets integrated with disruption indicators from international logistics activities. The dataset consisted of more than 5,000 operational records collected between 2018 and 2024. Several machine learning algorithms were implemented and compared, including Random Forest, Gradient Boosting, and Support Vector Machines. Experimental results indicate that the Gradient Boosting algorithm achieved the highest predictive performance with an accuracy of 94.2%. The model successfully identified key determinants of supply chain risk, including demand variability, supplier reliability, and transportation delays. These findings confirm that machine learning based predictive models can enhance supply chain resilience by enabling early risk detection and supporting proactive decision making in global logistics operations.]]>
Copyrights © 2026
