# Learning Points and Routes to Recommend Trajectories

arXiv: https://arxiv.org/abs/1608.07051 · HTML: https://mlsanity.com/paper/1608.07051/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Aug 2016.

## Built on by (most cited first, 13 of 13)

- [POIBERT: A Transformer-based Model for the Tour Recommendation Problem](https://mlsanity.com/paper/2212.13900/) (2022)
- [Enhancing Large Language Models for Mobility Analytics with Semantic Location Tokenization](https://mlsanity.com/paper/2506.11109/) (2025)
- [User Preferential Tour Recommendation Based on POI-Embedding Methods](https://mlsanity.com/paper/2103.02464/) (2021)
- [A Survey of Route Recommendations: Methods, Applications, and Opportunities](https://mlsanity.com/paper/2403.00284/) (2024)
- [Learning to Help Emergency Vehicles Arrive Faster: A Cooperative Vehicle-Road Scheduling Approach](https://mlsanity.com/paper/2202.09773/) (2022)
- [Real-time Spatio-temporal Event Detection on Geotagged Social Media](https://mlsanity.com/paper/2106.13121/) (2021)
- [DeepAltTrip: Top-k Alternative Itineraries for Trip Recommendation](https://mlsanity.com/paper/2109.03535/) (2021)
- [Adversarial Neural Trip Recommendation](https://mlsanity.com/paper/2109.11731/) (2021)
- [PLMTrajRec: A Scalable and Generalizable Trajectory Recovery Method with Pre-trained Language Models](https://mlsanity.com/paper/2410.14281/) (2024)
- [Point of Interest Recommendation: Pitfalls and Viable Solutions](https://mlsanity.com/paper/2507.13725/) (2025)
- [Analyzing and Mitigating Repetitions in Trip Recommendation](https://mlsanity.com/paper/2507.19798/) (2025)
- [VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction](https://mlsanity.com/paper/2509.19002/) (2025)
- [An Empirical Evaluation of Cross-City POI Recommendation on a Large-Scale Benchmark](https://mlsanity.com/paper/2608.27840/) (2026)

## Abstract (arXiv)

The problem of recommending tours to travellers is an important and broadly studied area. Suggested solutions include various approaches of points-of-interest (POI) recommendation and route planning. We consider the task of recommending a sequence of POIs, that simultaneously uses information about POIs and routes. Our approach unifies the treatment of various sources of information by representing them as features in machine learning algorithms, enabling us to learn from past behaviour. Information about POIs are used to learn a POI ranking model that accounts for the start and end points of tours. Data about previous trajectories are used for learning transition patterns between POIs that enable us to recommend probable routes. In addition, a probabilistic model is proposed to combine the results of POI ranking and the POI to POI transitions. We propose a new F1 score on pairs of POIs that capture the order of visits. Empirical results show that our approach improves on recent methods, and demonstrate that combining points and routes enables better trajectory recommendations.