Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Alif Al Hasan, Md. Musfique Anwar

TL;DR

SEAGET tackles next POI recommendation under realistic context by integrating seasonal dynamics, POI operating hours, and trajectory-driven signals within a graph-enhanced transformer. It redefines POI popularity through a balanced formula and combines a trajectory flow map-based GNN with contextual embeddings (POI-user, time-category, season-POI) and a transformer encoder, plus an operational time filter and multi-head MLP decoders. The approach yields improved accuracy and ranking metrics on the FourSquare-NYC dataset compared to a broad set of baselines, demonstrating the value of incorporating seasonality and open-hours constraints for context-aware recommendations. The work has practical implications for tourism and LBSN services, enabling more timely, feasible, and user-specific POI suggestions, with clear paths for extending to richer datasets and real-time operation-hour data.

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.

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

TL;DR

SEAGET tackles next POI recommendation under realistic context by integrating seasonal dynamics, POI operating hours, and trajectory-driven signals within a graph-enhanced transformer. It redefines POI popularity through a balanced formula and combines a trajectory flow map-based GNN with contextual embeddings (POI-user, time-category, season-POI) and a transformer encoder, plus an operational time filter and multi-head MLP decoders. The approach yields improved accuracy and ranking metrics on the FourSquare-NYC dataset compared to a broad set of baselines, demonstrating the value of incorporating seasonality and open-hours constraints for context-aware recommendations. The work has practical implications for tourism and LBSN services, enabling more timely, feasible, and user-specific POI suggestions, with clear paths for extending to richer datasets and real-time operation-hour data.

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.

Paper Structure

This paper contains 39 sections, 23 equations, 2 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Research Objectives
  3. Paper Outline
  4. Related Work
  5. Recent Advances in Recommendation Systems
  6. Next POI Recommendation
  7. Graphs in Next POI Recommendation
  8. Transformer-based Next POI Recommendation
  9. Seasonal Influence on the Next POI Recommendation
  10. Problem Formulation
  11. Our proposed model: SEAGET
  12. Our Popularity definition
  13. SEAGET Structure Overview
  14. Decoding the Trajectory Flow Map
  15. Learning POI Embedding
  16. ...and 24 more sections

Figures (2)

  • Figure 1: An overview of the SEAGET model.
  • Figure 2: Bar charts of all four accuracy metrices.