# POIFormer: A Transformer-Based Framework for Accurate and Scalable Point-of-Interest Attribution

arXiv: https://arxiv.org/abs/2507.09137 · HTML: https://mlsanity.com/paper/2507.09137/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 55 references that are in the map.
- First posted on arXiv 12 Jul 2025.

## Builds on (most cited first, 9 of 9)

- [Time2Vec: Learning a Vector Representation of Time](https://mlsanity.com/paper/1907.05321/) (2019)
- [Multi-Scale Representation Learning for Spatial Feature Distributions using Grid Cells](https://mlsanity.com/paper/2003.00824/) (2020)
- [MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Prediction](https://mlsanity.com/paper/2110.01401/) (2021)
- [Poly2Vec: Polymorphic Fourier-Based Encoding of Geospatial Objects for GeoAI Applications](https://mlsanity.com/paper/2408.14806/) (2024)
- [TrajGPT: Controlled Synthetic Trajectory Generation Using a Multitask Transformer-Based Spatiotemporal Model](https://mlsanity.com/paper/2411.04381/) (2024)
- [NUMOSIM: A Synthetic Mobility Dataset with Anomaly Detection Benchmarks](https://mlsanity.com/paper/2409.03024/) (2024)
- [Modelling of Bi-directional Spatio-Temporal Dependence and Users' Dynamic Preferences for Missing POI Check-in Identification](https://mlsanity.com/paper/2112.15285/) (2021)
- [Transferable Unsupervised Outlier Detection Framework for Human Semantic Trajectories](https://mlsanity.com/paper/2410.00054/) (2024)
- [Personalized Visited-POI Assignment to Individual Raw GPS Trajectories](https://mlsanity.com/paper/1901.06257/) (2019)

## Abstract (arXiv)

Accurately attributing user visits to specific Points of Interest (POIs) is a foundational task for mobility analytics, personalized services, marketing and urban planning. However, POI attribution remains challenging due to GPS inaccuracies, typically ranging from 2 to 20 meters in real-world settings, and the high spatial density of POIs in urban environments, where multiple venues can coexist within a small radius (e.g., over 50 POIs within a 100-meter radius in dense city centers). Relying on proximity is therefore often insufficient for determining which POI was actually visited. We introduce textsfPOIFormer, a novel Transformer-based framework for accurate and efficient POI attribution. Unlike prior approaches that rely on limited spatiotemporal, contextual, or behavioral features, textsfPOIFormer jointly models a rich set of signals, including spatial proximity, visit timing and duration, contextual features from POI semantics, and behavioral features from user mobility and aggregated crowd behavior patterns--using the Transformer's self-attention mechanism to jointly model complex interactions across these dimensions. By leveraging the Transformer to model a user's past and future visits (with the current visit masked) and incorporating crowd-level behavioral patterns through pre-computed KDEs, textsfPOIFormer enables accurate, efficient attribution in large, noisy mobility datasets. Its architecture supports generalization across diverse data sources and geographic contexts while avoiding reliance on hard-to-access or unavailable data layers, making it practical for real-world deployment. Extensive experiments on real-world mobility datasets demonstrate significant improvements over existing baselines, particularly in challenging real-world settings characterized by spatial noise and dense POI clustering.