Archetypes of urban travellers: Clustering of mobile phone users in Singapore

Abstract

An important task in transportation planning is to segment the travelling demand into groups of homogenous individuals for a better analysis. Traditionally travel demand is segmented through socio-demographic information. However, this information is often times not available in new streams of Big Data. We propose then a methodology to uncover the different archetypes of urban travellers based only on the mobility traces left by their mobile phones. We defined 5 variables that explain traits of travel behaviour within these digital traces, followed by an evaluation of two clustering algorithms on a dimensional-reduced space. We finally present 16 archetypes of urban travellers for the case of Singapore. Results from this study constitute one of the first steps towards the development of new Big Data travel demand models when privacy is a concern.