Generative Models for Synthetic Urban Mobility Data: A Systematic Literature Review

TL;DR

This paper systematically reviews generative models for creating synthetic urban mobility data, highlighting their potential to preserve privacy while maintaining data utility, and assessing their practical applicability.

Contribution

It provides a structured comparative overview of existing models and evaluates their practical use in generating synthetic urban mobility data.

Findings

Models effectively generate data resembling real urban mobility patterns.

Synthetic data can protect privacy while supporting research and planning.

Practical applicability varies across different generative approaches.

Abstract

Although highly valuable for a variety of applications, urban mobility data is rarely made openly available as it contains sensitive personal information. Synthetic data aims to solve this issue by generating artificial data that resembles an original dataset in structural and statistical characteristics, but omits sensitive information. For mobility data, a large number of corresponding models have been proposed in the last decade. This systematic review provides a structured comparative overview of the current state of this heterogeneous, active field of research. A special focus is put on the applicability of the reviewed models in practice.