Factory Reallocation & Shipping Optimization using AIML

This project presents a data-driven factory optimization system designed to improve logistics efficiency for Nassau Candy Distributor. The current approach relies on static factory allocation, which results in higher shipping lead times, increased operational costs, and inefficiencies in distribution. To address these challenges, a machine learning-based solution has been developed to predict shipping lead times based on product type, destination region, and shipping conditions. The system enables simulation of multiple factory–product assignment scenarios and evaluates their impact on delivery performance. An interactive dashboard has been implemented to allow stakeholders to analyze different scenarios in real time and receive recommendations for optimal factory allocation. The system identifies the most efficient factory options, helping reduce delays and improve overall logistics performance. This solution enhances decision-making by introducing predictive and scenario-based analysis, leading to improved operational efficiency, reduced delivery times, and scalable logistics planning. It can be further extended to support real-time data integration and cost optimization for large-scale distribution systems.