Car Ownership Behavior Model Considering Nonlinear Impacts of Multi-Scale Built Environment Characteristics

To explore the nonlinear influence of a multi-scale built environment on residents' car ownership behavior, combined with the data set of residents' individual information and travel-related data from the China Labor Force Dynamic Survey report, eight variables are selected to describe the built environment from multiple scales. The gradient-boosting iterative decision tree model including individual family attributes and neighborhood-scale and city-scale built-environment attributes is constructed. The results show that the individual family attributes have the greatest cumulative impact on car ownership behavior (46.3%). The built environment based on neighborhood scale and city scale also has a significant impact on residents' car ownership behavior, these being 33.94% and 19.76%, respectively. The distance to the city center at the neighborhood scale is positive correlated with car ownership. The number of buses per 10,000 people and road area per capita in the city scale are also positive correlated with car ownership. Therefore, in order to slow down the increase in car ownership, the built environment can be optimized and adjusted at neighborhood scale and city scale.