Zhang, YangCheng, Tao2018-11-062018-11-062018-09-079788490486894https://riunet.upv.es/handle/10251/111931[EN] With the wide application of the smart card technology in public transit system, traveller’s daily travel behaviours can be possibly obtained. This study devotes to investigating the pattern of individual mobility patterns and its relationship with social-demographics. We first extract travel features from the raw smart card data, including spatial, temporal and travel mode features, which capture the travel variability of travellers. Then, travel features are fed to various supervised machine learning models to predict individual’s demographic attributes, such as age group, gender, income level and car ownership. Finally, a case study based on London’s Oyster Card data is presented and results show it is a promising8Reconocimiento - No comercial - Sin obra derivada (by-nc-nd)Web dataInternet dataBig dataQCAPLSSEMConferenceSocial-demographicsSmart card dataTravel variabilityCapítulo de libro10.4995/CARMA2018.2018.8310Abierto