Investigating the Nonlinear Relationship Between Car Dependency and the Built Environment

Car-dominated daily travel has caused many severe and urgent urban problems across the world, such patterns have been found to be related built environment. However, few existing studies uncovered nonlinear relationship between environment car dependency using a machine learning method, thus failing provide policymakers with nuanced evidence-based guidance on reducing dependency. Using data from Puget Sound regional household surveys, this study analyzes complicated gradient boost decision tree method. The results show that people living in high-density areas are less likely rely private cars than those low-density neighborhoods. Both threshold effects observed relationships Increasing road density promotes usage when is below 6 km/km<sup>2</sup>. positive association use not high density. pedestrian-oriented decreases likelihood of as main mode. Such negative effect most effective over 14.5 More diverse land also discourages people’s use, probably because more promote active modes. Destination accessibility an overall significant These findings can help planners formulate tailored land-use interventions reduce