Enhancing supply chain agility with advanced weather forecasting

Abstract

This article presents a solution that leverages artificial intelligence techniques to enhance urban freight transportation planning and organization through the integration of weather forecasting data. We identify key challenges in the current urban logistics landscape and introduce a range of machine learning models designed to predict delivery delays. Logistic regression serves as the foundational model, analyzing historical delivery data in conjunction with weather conditions to assess the likelihood of delays, thus enabling informed decision-making for companies. Additionally, we evaluate two other machine learning models to determine the most effective approach for our specific context, assessing their accuracy and capacity to deliver actionable insights. By improving the predictive capabilities of urban freight systems, this research aims to streamline operations, reduce costs, and enhance overall service reliability, contributing to more efficient and resilient urban transportation networks.