Factory Reallocation & Shipping Optimization Recommendation System for Nassau Candy Distributor

Read full text Summarise with VIRAT
Authors: Nikhil M
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Developed a "Decision Intelligence" platform for Nassau Candy Distributor to optimize their supply chain network. The project shifts the organization from legacy, static factory-product assignments to an AI-driven reallocation model that balances shipping speed with regional profitability. The Problem: Nassau Candy’s traditional assignment rules led to suboptimal shipping distances, increased lead times in specific regions (like the Pacific and Atlantic corridors), and margin erosion due to logistics inefficiencies. There was no existing system to simulate "What-If" scenarios before making operational changes. Technical Execution: Predictive Analysis: Built and compared multiple machine learning models (Linear Regression, Random Forest, and Gradient Boosting) to forecast shipping lead times based on product type, origin factory, and destination region. Unsupervised Learning: Applied K-Means Clustering to categorize over 10,000 shipment routes into performance tiers, successfully identifying high-congestion bottlenecks. Optimization Engine: Developed a custom scoring logic that ranks factory reassignment recommendations based on a weighted 50/50 split of Lead Time Reduction and Profit Impact Stability. Cloud Deployment: Engineered a live, interactive dashboard using Streamlit and Plotly, allowing stakeholders to simulate reallocations and view real-time risk/impact alerts. Key Outcomes: Identified strategic reallocations capable of reducing average lead times by up to [Insert your result, e.g., 18%]. Achieved high model reliability with a Scenario Confidence Score based on robust R² and RMSE evaluation. Provided a scalable framework for Recommendation Coverage, identifying better alternatives for 60% of the current product catalog.

Fields of Study & Subjects

Impact of AI and Big Data on Business and Society Supply Chain and Inventory Management Business Logistics and Inventory Control

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
1 March 2026
Language
EN