Data-Driven Decision-Making in Transportation Management Using AI

The rapid growth of data generation and the advancements in artificial intelligence (AI) have opened up new opportunities for data-driven decision-making in transportation management. This article presents a comprehensive review of the applications of AI in transportation, focusing on machine learning techniques, optimization algorithms, and predictive analytics. The article proposes a novel AI-based decision-making framework that integrates data preprocessing, AI modeling, and performance evaluation to address complex transportation challenges. A case study on traffic congestion management is conducted to demonstrate the effectiveness of the proposed framework in reducing travel times and improving system efficiency compared to traditional methods. The results highlight the potential of AI in optimizing transportation operations and supporting informed decision-making. However, the article also discusses the limitations and challenges of implementing AI-based decision-making in transportation, such as data quality, privacy concerns, and computational requirements. Future research directions, including transfer learning, integration with emerging technologies, and explainable AI, are identified to facilitate the widespread adoption of AI-based decision-making in transportation management. The findings of this article contribute to the growing body of knowledge on data-driven intelligent transportation systems and provide valuable insights for researchers, practitioners, and policymakers in the field.