Large Language Models are Zero-Shot Next Location Predictors

Predicting the locations an individual will visit in the future is crucial for solving many societal issues like disease diffusion and pollution reduction. However, next-location predictors often require a significant amount of individual-level information that may be scarce or unavailable (e.g., in cold-start scenarios). Large Language Models (LLMs) have demonstrated strong generalization and reasoning capabilities while being rich in geographical knowledge, suggesting that they can operate as zero-shot next-location predictors. In our study, we evaluate over 15 LLMs on three real-world mobility datasets and find that they achieve accuracies up to 36.2%, representing a relative improvement of almost 640% compared to traditional models designed for human mobility. We further assess data contamination risks and explore the potential for using LLMs as text-based explainers for next-location predictions. Our results indicate that, irrespective of model size, LLMs can both predict and justify their decisions effectively.