Llama-Mob: Instruction-Tuning Llama-3-8B Excels in City-Scale Mobility Prediction

TL;DR

This paper introduces Llama-Mob, a fine-tuned large language model that significantly improves long-term citywide human mobility prediction and generalizes well across different urban environments.

Contribution

The study presents a novel instruction-tuned Llama-3-8B model specifically designed for long-term mobility prediction, demonstrating superior performance and zero-shot generalization capabilities.

Findings

Outperforms state-of-the-art in long-term mobility prediction

Exhibits strong zero-shot generalization to new cities

Can be extended to next POI prediction tasks

Abstract

Human mobility prediction plays a critical role in applications such as disaster response, urban planning, and epidemic forecasting. Traditional methods often rely on designing crafted, domain-specific models, and typically focus on short-term predictions, which struggle to generalize across diverse urban environments. In this study, we introduce Llama3-8B-Mob, a large language model fine-tuned with instruction tuning, for long-term citywide mobility prediction--in a Q&A manner. We validate our approach using large-scale human mobility data from four metropolitan areas in Japan, focusing on predicting individual trajectories over the next 15 days. The results demonstrate that Llama3-8B-Mob excels in modeling long-term human mobility--surpassing the state-of-the-art on multiple prediction metrics. It also displays strong zero-shot generalization capabilities--effectively generalizing to other cities even when fine-tuned only on limited samples from a single city. Moreover, our method is general and can be readily extended to the next POI prediction task. For brevity, we refer to our model as Llama-Mob, and the corresponding results are included in this paper. Source codes are available at https://github.com/TANGHULU6/Llama3-8B-Mob.