In this presentation, we propose a model for the simultaneous choice of activity types, order, start times and durations of activity episodes in a sequence. In particular, we develop a framework for choice set generation based on path choice to deal with the large choice set. The activity-episode sequence is modeled as a path in an activity network defining the activity type, duration and time of day. The large dimensionality of the choice set is managed through a strategic sampling using a Metropolis-Hastings algorithm. Our model can be used to forecast demand at the urban scale. Since it does not assume tours, it can also be applied to pedestrian facilities, such as transport hubs or mass gathering. A case study using WiFi traces on a campus is presented.