Out-of-Town Recommendation with Travel Intention Modeling

TL;DR

This paper introduces TRAINOR, a novel framework for out-of-town POI recommendation that models complex travel intentions using graph neural networks, neural topic models, and matrix factorization, validated by real-world data.

Contribution

The paper proposes a comprehensive travel intention-aware recommendation framework that integrates GNNs, neural topic modeling, and matrix factorization for improved out-of-town POI recommendations.

Findings

Effective in capturing complex travel intentions

Outperforms existing out-of-town recommenders

Provides meaningful explanations for travel purposes

Abstract

Out-of-town recommendation is designed for those users who leave their home-town areas and visit the areas they have never been to before. It is challenging to recommend Point-of-Interests (POIs) for out-of-town users since the out-of-town check-in behavior is determined by not only the user's home-town preference but also the user's travel intention. Besides, the user's travel intentions are complex and dynamic, which leads to big difficulties in understanding such intentions precisely. In this paper, we propose a TRAvel-INtention-aware Out-of-town Recommendation framework, named TRAINOR. The proposed TRAINOR framework distinguishes itself from existing out-of-town recommenders in three aspects. First, graph neural networks are explored to represent users' home-town check-in preference and geographical constraints in out-of-town check-in behaviors. Second, a user-specific travel intention is formulated as an aggregation combining home-town preference and generic travel intention together, where the generic travel intention is regarded as a mixture of inherent intentions that can be learned by Neural Topic Model (NTM). Third, a non-linear mapping function, as well as a matrix factorization method, are employed to transfer users' home-town preference and estimate out-of-town POI's representation, respectively. Extensive experiments on real-world data sets validate the effectiveness of the TRAINOR framework. Moreover, the learned travel intention can deliver meaningful explanations for understanding a user's travel purposes.