Understanding public transit patterns with open geodemographics to facilitate public transport planning

This is the authors' abstract. We don't add key points for this paper.

Plentiful studies have discussed the potential applications of contactless card from understanding interchange patterns to transit analysis and user classifications. However, the incomplete anonymous nature of the smart card data inherently limit the and understanding of thefindings, whichfurther limit implementations. Geodemographics, as ‘an analysis of people where they live’, can be utilised as a promising supplement provide contextual information to transport planning. This paper a methodological framework that conjointly integrates personalised card data with open geodemographics so as to pursue better understanding of the traveller’s behaviours. It adopts text mining technology, latent Dirichlet allocation modelling, to the transit patterns from the personalised smart card data then use the open geodemographics derived from census data enhance the interpretation of the patterns. Moreover, it presents tube as an example to illustrate its potential usefulness in transport planning.