Optimizing Logistics: A Data Driven Approach for Company Z’s Vehicle Routing Problem

Abstract

Abstract: The Vehicle Routing Problem(VRP) remains a pivotal challenge in logistics optimization, particularly for industries requiring efficient routing solutions. This research addresses the VRP within the context of Company Z , a key player in the manufacturing and automotive sector, aiming to enhance its supply chain efficiency. By leveraging advanced data science techniques and optimization algorithms, specifically the Teaching-Learning-Based Optimization (TLBO) algorithm, we develop a robust framework to minimize travel time and operational costs. The proposed approach integrates real-world data to inform route planning and validate algorithmic performance. This study not only provides actionable insights for logistical improvements but also visually represents the optimized routes, thereby demonstrating the practical applicability and benefits of the developed solutions. The results indicate significant improvements in route efficiency and resource allocation, underscoring the potential of data-driven methods in solving complex logistical problems.