Large Language Models for Spatial Trajectory Patterns Mining

• DOI: 10.48550/arxiv.2310.04942
• Publication Date: 2023-01-01
• Authors: Zheng Zhang; Hossein Amiri; Zhenke Liu; Andreas Züfle; Liang Zhao
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; Machine Learning (cs.LG)

Identifying anomalous human spatial trajectory patterns can indicate dynamic changes in mobility behavior with applications domains like infectious disease monitoring and elderly care. Recent advancements large language models (LLMs) have demonstrated their ability to reason a manner akin humans. This presents significant potential for analyzing temporal mobility. In this paper, we conduct empirical studies assess the capabilities of leading LLMs GPT-4 Claude-2 detecting behaviors from data, by comparing specialized methods. Our key findings demonstrate that attain reasonable anomaly detection performance even without any specific cues. addition, providing contextual clues about irregularities could further enhances prediction efficacy. Moreover, provide explanations judgments, thereby improving transparency. work provides insights on strengths limitations analysis.