Mining activity pattern trajectories and allocating activities in the network

GPS enabled devices, generating high‐resolution spatial–temporal data, are opening new lines of possibilities for transportation applications in both planning and research. Mining these rich and large datasets to infer people’s travel behavior, the activity patterns resulting from their behavior, and allocating activities in the network is the focus of this paper. Here we introduce a methodology that relies only on geocoded location data and socioeconomic characteristics to infer types of activities in which individuals engage at different locations in the network. Depending on the duration of the stop, arrival time and geographic distance to home location and previous activities, the type of activity is inferred at the census tract level using adaptive boosting algorithm. Then, using a model based on Markov chains with conditional random field to capture dependency between activity sequencing and individuals’ socioeconomic attributes, the spatial–temporal trajectory of activity/travel engagement is generated. The model is trained on data obtained from the California Household Travel Survey data 2000–2001 and subsequently applied to an out‐of sample test set to validate the accuracy and performance.