.png){kind=icon}
.png){kind=icon}
Return
LLM-PDM: An LLM Persona-Driven Method for replicating personal mobility preferences at scale
.png){kind=icon}
PRE
AI
I
S
C
DOI：10.26599/COMMTR.2026.9640004.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Traditional travel surveys are costly, time-consuming and face declining response rates, motivating the exploration of artificial data generation methods. In this research, we propose a novel Persona-Driven Method (PDM) for generating synthetic mobility survey data via large language models (LLMs). The method defines representative personas-each characterized by specific sociodemographic attributes-and prompts an LLM to emulate survey respondents with these personas. A guided prompting strategy is introduced to calibrate the synthetic data distributions so that they closely match real-world population statistics. We evaluate the approach on the German MiD 2017 (Mobilit & auml;t in the Deutschland 2017) dataset. The quality of the LLM-PDM-generated synthetic data is assessed against ground truth data via a comprehensive set of metrics, including the mean absolute error (MAE), root mean square error (RMSE), Jensen-Shannon distance (JSD), entropy, conditional entropy and the Earth Mover's distance (EMD). The empirical results demonstrate that the LLM-PDM approach produces high-fidelity synthetic populations that preserve key distributions and relationships present in real data. Across the case studies, the LLM-PDM method achieves low distributional errors (e.g., MAE < 3%) and captures important joint patterns, significantly outperforming a number of LLM baselines.
Keywords:
synthetic data generation
travel survey
large language models (LLMs)
Persona-Driven Modeling (PDM)
prompt engineering
synthetic populations
mobility data
Journal
IF:
14.5
Papers:
216
Citations:
915
Organization
Cited Papers