Abstract
Extensive research has been conducted exploring associations between built environment characteristics and biking. However, these approaches have often lacked the ability to understand the interactions of the built environment, population and bicycle ridership. To overcome these limitations, this study aimed to develop novel urban biking typologies using unsupervised machine learning methods. We conducted a retrospective analysis of travel surveys, bicycle infrastructure and population and land use characteristics in the Greater Melbourne region, Australia. To develop the urban biking typology, we used a k-medoids clustering method. Analyses revealed 5 clusters. We highlight areas with high bicycle network density and a high proportion of trips made by bike (Cluster 1; reflecting 12% of the population of Greater Melbourne, but 57% of all bike trips) and areas with high off-road and on-road bicycle network length, but a low proportion of trips made by bike (Cluster 4, reflecting 23% of the population of Greater Melbourne and 13% of all bike trips). Our novel approach to developing an urban biking typology enabled the exploration of the interaction of bicycle ridership, the bicycle network, population and land use characteristics. Such approaches are important in advancing our understanding of bicycling behaviour, but further research is required to understand the generalisability of these findings to other settings.