This article presents an analysis of current trends in the digitalization of the transport industry, focusing on the relationship between its advantages and corresponding potential opportunities. The study aims to identify potential opportunities arising from the integration of digital technologies and artificial intelligence (AI) in the transport sector. To achieve this goal, the principles and methodological foundations for the use of artificial intelligence in the digitalization of the transport industry are reviewed and analyzed. Complex linear and nonlinear relationships exist among the technical and operational parameters of the railway system; therefore, the study used statistical correlation analysis and machine-learning (ML) methods. ML methods are effective at identifying hidden patterns in large datasets (such as train movements) and improving forecasting accuracy. The scientific novelty of the study lies in the development of an integrated model for assessing the impact of digital technologies and machine-learning methods on the efficiency of the transport system. A machine-learning model for predicting train delays based on key operational factors of the railway infrastructure was developed. A model of balanced factors influencing the time and efficiency of the transport process was proposed, including a practical framework for implementing artificial intelligence in train schedule optimization. A cost-effectiveness calculation based on a 20% reduction in train delays yielded an estimated economic benefit of approximately 73.72 billion soums per year. The underlying cost-per-minute-of-delay figure (799,472 soums) is used as a fixed input to this calculation; its derivation (e.g., the cost components included, whether it is based on a specific study, tariff schedule, or official estimate, and the reference year/exchange rate/inflation assumptions) is not documented in the present manuscript and should be reported explicitly, since it materially affects the economic-impact estimate. The methodological basis of the research includes machine-learning modelling and comparative analytical forecasting methods used to study the implementation of intelligent systems and analyze their impact on the efficiency, safety, and sustainability of transport systems.