GeoGR: A Generative Retrieval Framework for Spatio-Temporal Aware POI Recommendation

TL;DR

GeoGR is a novel framework that combines geographic-aware semantic tokenization and multi-stage language model training to improve spatio-temporal POI recommendation accuracy and scalability in large-scale navigation services.

Contribution

It introduces a two-stage approach integrating geographic tokenization and advanced LLM training for intent-aware POI recommendation in complex environments.

Findings

GeoGR outperforms state-of-the-art baselines in real-world datasets.

Deployment on AMAP shows significant online metric improvements.

Framework demonstrates practical scalability and effectiveness.

Abstract

Next Point-of-Interest (POI) prediction is a fundamental task in location-based services, especially critical for large-scale navigation platforms like AMAP that serve billions of users across diverse lifestyle scenarios. While recent POI recommendation approaches based on SIDs have achieved promising, they struggle in complex, sparse real-world environments due to two key limitations: (1) inadequate modeling of high-quality SIDs that capture cross-category spatio-temporal collaborative relationships, and (2) poor alignment between large language models (LLMs) and the POI recommendation task. To this end, we propose GeoGR, a geographic generative recommendation framework tailored for navigation-based LBS like AMAP, which perceives users' contextual state changes and enables intent-aware POI recommendation. GeoGR features a two-stage design: (i) a geo-aware SID tokenization pipeline that explicitly learns spatio-temporal collaborative semantic representations via geographically constrained co-visited POI pairs, contrastive learning, and iterative refinement; and (ii) a multi-stage LLM training strategy that aligns non-native SID tokens through multiple template-based continued pre-training(CPT) and enables autoregressive POI generation via supervised fine-tuning(SFT). Extensive experiments on multiple real-world datasets demonstrate GeoGR's superiority over state-of-the-art baselines. Moreover, deployment on the AMAP platform, serving millions of users with multiple online metrics boosting, confirms its practical effectiveness and scalability in production.