Birds of a Feather Cluster Nearby: a Proximity-Aware Geo-Codebook for Local Service Recommendation

TL;DR

Pro-GEO introduces a proximity-aware geo-codebook that jointly models semantic relevance and geographic proximity, significantly improving local service recommendations.

Contribution

It proposes a novel geo-centroid coordinate system and rotational encoding to incorporate geographic constraints into semantic tokenization.

Findings

Reduces average geographic clustering distance by 45.60%

Achieves 1.87% improvement in Hit@50

Outperforms state-of-the-art methods on large-scale data

Abstract

Generative recommendation systems are increasingly adopted in local service platforms, where semantic relevance alone is insufficient without strict geographic feasibility. A key technical challenge lies in semantic ID (SID) tokenization, which directly impacts the recommendation performance. However, existing semantic codebooks neglect geographic constraints, often resulting in recommendations that are semantically relevant yet geographically unreachable. To address this limitation, we propose Pro-GEO, a Proximity-aware GEO-codebook. Pro-GEO establishes a geo-centroid local coordinate system to capture intra-cluster spatial relationships and a geo-rotary position encoding mechanism that models geographic proximity as orthogonal rotational transformations in the high-dimensional embedding. This design enables semantic and spatial signals to be jointly modeled in a balanced manner, without reducing geographic information to a weak auxiliary feature. Extensive experiments conducted on a large-scale industrial dataset reveal that Pro-GEO significantly outperforms state-of-the-art methods. In particular, Pro-GEO reduces the average geographic clustering distance by 45.60% and achieves a 1.87% improvement in Hit@50, highlighting its effectiveness for real-world local service recommendation.