Next Point of Interest (POI) Recommendation System Driven by User Probabilistic Preferences and Temporal Regularities

Fengyu Liu, Jinhe Chen, Jun Yu and Rui Zhong ()
Additional contact information
Fengyu Liu: College of Information Technology, Shanghai Ocean University, Shanghai 201306, China
Jinhe Chen: Tianyou College, East China Jiaotong University, Nanchang 330013, China
Jun Yu: Institute of Science and Technology, Niigata University, Niigata 950-2181, Japan
Rui Zhong: Information Initiative Center, Hokkaido University, Sapporo 060-0808, Japan

Mathematics, 2025, vol. 13, issue 8, 1-22

Abstract: The Point of Interest (POI) recommendation system is a critical tool for enhancing user experience by analyzing historical behaviors, social network data, and real-time location information with the increasing demand for personalized and intelligent services. However, existing POI recommendation systems face three major challenges: (1) oversimplification of user preference modeling, limiting adaptability to dynamic user needs, (2) lack of explicit arrival time modeling, leading to reduced accuracy in time-sensitive scenarios, and (3) complexity in trajectory representation and spatiotemporal mining, posing difficulties in handling large-scale geographic data. This paper proposes NextMove, a novel POI recommendation model that integrates four key modules to address these issues. Specifically, the Probabilistic User Preference Generation Module first employs Latent Dirichlet Allocation (LDA) and a user preference network to model user personalized interests dynamically by capturing latent geographical topics. Secondly, the Self-Attention-based Arrival Time Prediction Module utilizes a Multi-Head Attention Mechanism to extract time-varying features, improving the precision of arrival time estimation. Thirdly, the Transformer-based Trajectory Representation Module encodes sequential dependencies in user behavior, effectively capturing contextual relationships and long-range dependencies for accurate future location forecasting. Finally, the Next Location Feature-Aggregation Module integrates the extracted representation features through an FC-based nonlinear fusion mechanism to generate the final POI recommendation. Extensive experiments conducted on real-world datasets demonstrate the superiority of the proposed NextMove over state-of-the-art methods. These results validate the effectiveness of NextMove in modeling dynamic user preferences, enhancing arrival time prediction, and improving POI recommendation accuracy.

Keywords: POI recommendations; Transformer; Self-Attention; generative probabilistic modeling; personalized user preferences; arrival time prediction (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/8/1232/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/8/1232/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:8:p:1232-:d:1631003

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().