Neural Optimization for Pharmaceutical Transportation Under Stressful Conditions

This study presents a refined model for supply chain competition in the transportation of pharmaceutical items, in stress conditions characterized by high demands of critical items and closures. Each shipper aims to minimize its costs by optimizing the parameters of the defined cost function by means of a supervised learning approach which exploits an Artificial Neural Network model. Given the challenges posed by emergency situations, we focus our attention on the imperative to optimize transportation costs from the shipper to the destination, while considering the mode of shipment. Specifically, our analysis leverages the Health dataset from US Supply Chain Information for COVID-19 to investigate supply chain shipments during the COVID-19 pandemic, a period marked by significant logistical challenges in meeting demand and minimizing the cost across various destination countries. Finally, through this methodology, we present an illustrative example to observe the optimal supply chain solutions using a Neural Optimization Machine.