Generating daily activity schedules using machine learning Master Thesis Sergej Gasparovich June 19, 2020 Prof. M. Bierlaire, J. Pougala, T. Hillel Transport and Mobility Laboratory, EPFL Y. Liu Visual Intelligence
The study of how people schedule their daily activities is of interest in the context of transport demand forecasting using activity based-models, where activity schedules are generated in order to estimate the trip demand they produce. Machine learning has achieved efficient results in a number of areas due to its strong data processing capacity and can be useful for demand forecast models. This paper demonstrates for the first time how Generative Adversarial Networks (GAN) can be applied in this context. We create a GAN model adapted for the specificity of the task, capable of working with discrete data and generating feasible daily activity patterns based on data of Swiss residents from the MTMC 2015 data set. We also show how we can condition our model to generate patterns for distinct days of the week. This work can be used as a framework for the activity generation step for activity-based modelling, in order to provide accurate and diverse activity schedules predictions using machine learning.
2020-07-14
58 pages