STrajRAG: Supervised trajectory retrieval augmented generation for next POI recommendation with travel semantics

A Point-of-Interest (POI) refers to a specific place of potential interest in location-based system. Next POI recommendation based on Large Language Models (LLMs) transforms the recommendation task into a question-answering task to predict the next waypoint along a trajectory to enhance user experience . While existing research has made preliminary attempts, there are inherent limitations: (1) Without sufficient exploration of POI, user and temporal similarities between trajectories in the historical data , previous studies may fail to include the next POI in the prompt, inherently limiting the ability of LLMs to make accurate predictions; (2) Existing methods do not account for candidates derived from various travel semantics and employs a sample-based generation strategy, which provides duplicate outcomes. To address these issues, we propose an LLM-based model named STrajRAG. Our model introduces a supervised auxiliary task to facilitate the identification of trajectories including the next POI, integrating heterogeneous similarities such as user and time. We consider candidates based on spatial distances and overall transition frequencies, employing beam search to generate diverse outcomes. Extensive experiments on three datasets demonstrate that STrajRAG achieves a 3%–32% performance improvement across diverse metrics compared to existing state-of-the-art methods. • Proposes an LLM-based framework for next Point-of-Interest recommendation. • Introduces an auxiliary task to retrieve trajectories including the target. • Considers more candidates based on spatial distance and transition frequencies. • Employs beam search in the generation stage for a wider search space. • Validates the framework on three datasets with multiple metrics.