Enhanced Supply Chain Risk Management Using K-Means Clustering and Tableau: A Hybrid Framework for Big Data Visualization

In the context of increasingly complex global supply chains, effective risk management has become a critical challenge. This study presents a hybrid computational framework that integrates K-means clustering and Tableau to address supply chain risks comprehensively. The framework transforms heterogeneous supply chain data, including supplier performance, logistics disruptions, and demand variability, into actionable insights. By applying the K-means algorithm, risks are segmented into distinct categories such as high-risk suppliers, vulnerable logistics routes, and volatile demand clusters. The segmentation process is further enhanced through advanced metrics such as the Davies-Bouldin Index and Silhouette Score, ensuring well-defined clusters. Tableau is utilized to visualize these clusters through interactive dashboards, including heatmaps, scatter plots, and trendlines, which enable decision-makers to interpret and act on the results efficiently. The framework was validated using real-world supply chain data from a multinational manufacturing company. Results demonstrated the identification of critical risk factors, effective categorization of risks, and improved decision-making capabilities. For instance, high-risk suppliers were identified based on low reliability and significant delivery delays, while high-disruption logistics routes were highlighted through heatmaps. The integration of clustering and visualization facilitated actionable decisions, such as optimizing inventory policies and renegotiating logistics contracts, resulting in measurable improvements in supply chain resilience. This study underscores the potential of combining computational analytics with visualization tools, offering a scalable and systematic approach to modern supply chain risk management.