Advancing urban transportation planning: a comparative analysis of machine learning and conventional regression-based trip generation models

Abstract

Urbanization is a global phenomenon that continuously reshapes the dynamics of the world [1].By 2050, the United Nations predicts that almost two-thirds of the world's population will reside in cities [2].The effective and sustainable management of transportation systems is a crucial factor as cities continue to expand and change [3].Accurate trip generation prediction is crucial for urban transportation planning to address rising travel demands, reduce congestion, minimize environmental impacts, and enhance overall quality of life [4]. *Author for correspondenceTrip generation models are essential in transportation planning, forming the foundation for estimating travel demand based on various socio-economic and land-use factors.Traditionally, these models have been developed using linear regression techniques, which rely on a linear relationship between dependent and independent variables.While linear regression models are straightforward to implement and interpret, they often fail to capture the complexities and nonlinearities inherent in real-world travel behavior.As transportation systems become more intricate and data availability increases, there is a growing need for more sophisticated modeling techniques that offer greater predictive accuracy and model robustness.Trip generation models have

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 6 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.