Machine learning-based analysis of factors influencing bus station traffic management in India

Rapid urbanization and increased private vehicle ownership have significantly intensified traffic congestion in Indian cities. In response, the Indian government has implemented various initiatives to strengthen public transportation, with buses constituting the predominant mode of urban transit. Consequently, the need to upgrade bus terminal infrastructure has become critical to support growing passenger volume and operational complexity. This study aims to prioritize the key factors influencing the functional performance of bus stations. A preliminary site investigation was conducted to assess existing infrastructural conditions, followed by comprehensive data collection through traffic surveys and structured questionnaires. Statistical analyses including Chi-squared test, validated the survey data. Integrated principal component and multi criteria decision analysis was employed to rank influential factors. Item rate analysis determined cost-sensitive components. Cluster analysis was used to assess interrelationships among variables. The results offer a robust, data-driven framework for optimizing future bus terminal planning and design with the proposed layout.