Bridging Gaps in Transport Demand Forecasting through Artificial Intelligence and Machine Learning

Artificial Intelligence (AI) has emerged as a transformative tool for transportation demand forecasting, addressing the limitations of traditional statistical approaches. This study systematically reviews recent literature to evaluate AI methodologies, their applications, and the systemic factors that shape adoption. Peer-reviewed studies published between 2018 and 2025 were identified from Scopus, Web of Science, and Google Scholar. Findings reveal that AI techniques, particularly deep learning and ensemble models, consistently outperform conventional forecasting methods in predictive accuracy and adaptability. Integration of spatio-temporal and geospatial data further enhances model robustness, supporting more responsive strategies for sustainable urban mobility. Applications span passenger transport, freight logistics, public transit optimization, and electric vehicle charging demand. Nonetheless, challenges persist, including data scarcity, computational demands, interpretability concerns, and uneven adoption between developed and developing regions. The review underscores the need for supportive policies, collaborative data management, and fairness-aware models. Overall, leveraging AI in transport forecasting is essential to build efficient, adaptive, and inclusive mobility systems while aligning future research with long-term planning and sustainability goals.