TransMode-LLM: Feature-Informed Natural Language Modeling with Domain-Enhanced Prompting for Travel Behavior Modeling

TL;DR

This paper introduces TransMode-LLM, a novel framework combining statistical analysis and large language models to predict travel modes from survey data, demonstrating improved accuracy with few-shot learning and domain-enhanced prompting.

Contribution

It presents an innovative integration of statistical features and LLM techniques for travel mode prediction, exploring the effects of domain prompting and few-shot learning across different LLM architectures.

Findings

Few-shot learning improves accuracy up to 42.9%.

Domain-enhanced prompting benefits general-purpose models.

Performance effects of domain prompting vary across LLM types.

Abstract

Understanding traveler behavior and accurately predicting travel mode choice are at the heart of transportation planning and policy-making. This study proposes TransMode-LLM, an innovative framework that integrates statistical methods with LLM-based techniques to predict travel modes from travel survey data. The framework operates through three phases: (1) statistical analysis identifies key behavioral features, (2) natural language encoding transforms structured data into contextual descriptions, and (3) LLM adaptation predicts travel mode through multiple learning paradigms including zero-shot and one/few-shot learning and domain-enhanced prompting. We evaluate TransMode-LLM using both general-purpose models (GPT-4o, GPT-4o-mini) and reasoning-focused models (o3-mini, o4-mini) with varying sample sizes on real-world travel survey data. Extensive experiment results demonstrate that the LLM-based approach achieves competitive accuracy compared to state-of-the-art baseline classifiers models. Moreover, few-shot learning significantly improves prediction accuracy, with models like o3-mini showing consistent improvements of up to 42.9\% with 5 provided examples. However, domain-enhanced prompting shows divergent effects across LLM architectures. In detail, it is helpful to improve performance for general-purpose models with GPT-4o achieving improvements of 2.27% to 12.50%. However, for reasoning-oriented models (o3-mini, o4-mini), domain knowledge enhancement does not universally improve performance. This study advances the application of LLMs in travel behavior modeling, providing promising and valuable insights for both academic research and transportation policy-making in the future.