Synthesising activity participations and scheduling with deep generative machine learning

Using a deep generative machine learning approach, we synthesise human activity participations and scheduling; i.e. the choices of what activities to participate in and when. Activity schedules are a core component of many applied transport, energy, and epidemiology models. Our data-driven approach directly learns the distributions resulting from human preferences and scheduling logic without the need for complex interacting combinations of sub-models and custom rules. This makes our approach significantly faster and simpler to operate than existing approaches to synthesise or anonymise schedule data. We additionally contribute a novel schedule representation and a comprehensive evaluation framework. We evaluate a range of schedule encoding and deep model architecture combinations. The evaluation shows our approach can rapidly generate large, diverse, novel, and realistic synthetic samples of activity schedules. • We contribute a novel approach to synthesising human activity schedules using deep generative modelling. • Specifically, we demonstrate the rapid synthesis of realistic human activity schedules using Variational Auto-Encoders. • We propose an activity schedule encoding, using a continuous encoding of activity durations. • We present a comprehensive density estimating framework for evaluating the quality of model outputs.