An Adaptive Framework of Geographical Group-Specific Network on O2O Recommendation

TL;DR

This paper introduces GeoGrouse, an adaptive geographical group-specific modeling framework for O2O recommendation that enhances personalization by capturing local user preferences and improves business outcomes.

Contribution

It proposes a novel automatic geographical grouping method and a group-specific modeling approach to better capture user preferences across different regions.

Findings

Effective in capturing regional user preferences

Significant improvements in recommendation accuracy

Substantial business performance enhancement

Abstract

Online to offline recommendation strongly correlates with the user and service's spatiotemporal information, therefore calling for a higher degree of model personalization. The traditional methodology is based on a uniform model structure trained by collected centralized data, which is unlikely to capture all user patterns over different geographical areas or time periods. To tackle this challenge, we propose a geographical group-specific modeling method called GeoGrouse, which simultaneously studies the common knowledge as well as group-specific knowledge of user preferences. An automatic grouping paradigm is employed and verified based on users' geographical grouping indicators. Offline and online experiments are conducted to verify the effectiveness of our approach, and substantial business improvement is achieved.