Improving Public Transportation Efficiency Through Accurate Bus Passenger Demand

Abstract

This paper highlights the significance of efficient management of public transportation systems for providing high-quality service to passengers. The prediction of bus occupancy levels plays a critical role in optimizing bus routes, improving service reliability, and reducing passenger wait times. However, there is a lack of research in this area, and most existing studies focus on either real-time sensor data or historical bus occupancy data. This paper aims to establish a benchmark for bus and other public transport systems by using traditional and machine learning techniques to build models that can accurately predict bus occupancy levels. The main contribution of the study is to create an initial passenger demand with a specific environmental setup and evaluate the performance of the approach using a dataset collected from a real-world bus system. Through experimental simulations, the authors hope to identify long-term issues in the public transportation system and prevent possible problems, such as bottlenecks, shortages during rush hours, or wastage of resources. The paper emphasizes the importance of accurate bus passenger demand and highlights the need for further research in this area to enhance the efficiency and reliability of public transportation systems.