Walkability is much studied, but the relative importance of perceptions and motivations is still not consensual. This study took a holistic approach to examine the comparative importance of a range of possible perceptions, motivations and individual characteristics on walking levels.

Data from Auckland Transport's Active Modes online survey (AT survey, N = 4,114) captured environmental perceptions and travel behaviour. Machine learning (gradient boosting) was used to predict walking levels from perceptual data and individual characteristics and determine the relative importance of each variable. Strong predictors of walking included the use of public transport, walking perceived as saving money and avoiding parking hassle, age group, and overall satisfaction with walking. Surprisingly, the importance of expected dimensions such as perceived availability of destinations or internal motivations was null in the general model.

These findings suggest a more holistic view of walking behaviour is needed, one that moves beyond the pure availability of destinations.

关于步行的研究很多，但是知觉和动机的相对重要性仍然没有达成共识。这项研究采用整体方法来检验步行水平上各种可能的感知，动机和个人特征的相对重要性。

奥克兰交通局的“主动模式”在线调查（AT调查，N = 4,114）收集的数据反映了人们对环境的感知和旅行行为。机器学习（梯度提升）用于根据感知数据和个人特征预测步行水平，并确定每个变量的相对重要性。强烈预测步行的因素包括使用公共交通工具，步行被认为是省钱和避免停车麻烦，年龄组以及对步行的总体满意度。令人惊讶的是，在一般模型中，预期维度（例如目的地的感知可用性或内部动机）的重要性为零。

这些发现表明，需要一种更全面的步行行为观点，这种观点超越了目的地的纯粹可用性。