SEAGET: Seasonal and Active hours guided Graph Enhanced Transformer for the next POI recommendation

2025-03-27

AI Summary

To address low accuracy and poor contextual plausibility in next-POI recommendation—particularly in tourism scenarios—this paper proposes a graph-enhanced Transformer model integrating multi-source spatiotemporal dynamic features. We innovatively jointly model POI seasonal popularity, real-time operational status, and fine-grained temporal activity to reconstruct a more realistic definition of POI popularity. Additionally, we design a multimodal feature fusion mechanism that jointly captures user preferences, geographical constraints, temporal context, and dynamic environmental factors. Extensive experiments on multiple real-world trajectory datasets demonstrate that our method significantly outperforms existing state-of-the-art approaches, achieving average improvements of 12.6% in Recall@10 and MRR. The model not only enhances prediction accuracy but also provides contextual interpretability, offering a practical, deployable solution for personalized location-based services.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

One of the most important challenges for improving personalized services in industries like tourism is predicting users' near-future movements based on prior behavior and current circumstances. Next POI (Point of Interest) recommendation is essential for helping users and service providers by providing personalized recommendations. The intricacy of this work, however, stems from the requirement to take into consideration several variables at once, such as user preferences, time contexts, and geographic locations. POI selection is also greatly influenced by elements like a POI's operational status during desired visit times, desirability for visiting during particular seasons, and its dynamic popularity over time. POI popularity is mostly determined by check-in frequency in recent studies, ignoring visitor volumes, operational constraints, and temporal dynamics. These restrictions result in recommendations that are less than ideal and do not take into account actual circumstances. We propose the Seasonal and Active hours-guided Graph-Enhanced Transformer (SEAGET) model as a solution to these problems. By integrating variations in the seasons, operational status, and temporal dynamics into a graph-enhanced transformer framework, SEAGET capitalizes on redefined POI popularity. This invention gives more accurate and context-aware next POI predictions, with potential applications for optimizing tourist experiences and enhancing location-based services in the tourism industry.

Problem

• Predicting users' near-future movements for personalized tourism services
• Considering user preferences, time contexts, and geographic locations simultaneously
• Addressing POI popularity dynamics, operational status, and seasonal desirability

Innovation

• Graph-enhanced transformer for POI recommendation
• Integrates seasonal and active hours dynamics
• Redefines POI popularity with contextual factors