# Trajectory Test-Train Overlap in Next-Location Prediction Datasets

arXiv: https://arxiv.org/abs/2203.03208 · HTML: https://mlsanity.com/paper/2203.03208/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 62 references that are in the map.
- First posted on arXiv 7 Mar 2022.

## Builds on (most cited first, 14 of 14)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Generalizing from a Few Examples: A Survey on Few-Shot Learning](https://mlsanity.com/paper/1904.05046/) (2019)
- [Generalization in Deep Learning](https://mlsanity.com/paper/1710.05468/) (2017)
- [Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets](https://mlsanity.com/paper/2008.02637/) (2020)
- [STAN: Spatio-Temporal Attention Network for Next Location Recommendation](https://mlsanity.com/paper/2102.04095/) (2021)
- [A Survey on Deep Learning for Human Mobility](https://mlsanity.com/paper/2012.02825/) (2020)
- [Dilated Recurrent Neural Networks](https://mlsanity.com/paper/1710.02224/) (2017)
- [What do Models Learn from Question Answering Datasets?](https://mlsanity.com/paper/2004.03490/) (2020)
- [Challenges in Generalization in Open Domain Question Answering](https://mlsanity.com/paper/2109.01156/) (2021)
- [A Survey of Location Prediction on Twitter](https://mlsanity.com/paper/1705.03172/) (2017)
- [An analytical framework to nowcast well-being using mobile phone data](https://mlsanity.com/paper/1606.06279/) (2016)
- [Quantifying the sustainability impact of Google Maps: A case study of Salt Lake City](https://mlsanity.com/paper/2111.03426/) (2021)

## Built on by (most cited first, 3 of 3)

- [Large Language Models are Zero-Shot Next Location Predictors](https://mlsanity.com/paper/2405.20962/) (2024)
- [The Urban Impact of AI: Modeling Feedback Loops in Next-Venue Recommendation](https://mlsanity.com/paper/2504.07911/) (2025)
- [ORBITER: Conflict-Aware Decision-Making for Agentic Last-Mile Delivery](https://mlsanity.com/paper/2608.18846/) (2026)

## Abstract (arXiv)

Next-location prediction, consisting of forecasting a user's location given their historical trajectories, has important implications in several fields, such as urban planning, geo-marketing, and disease spreading. Several predictors have been proposed in the last few years to address it, including last-generation ones based on deep learning. This paper tests the generalization capability of these predictors on public mobility datasets, stratifying the datasets by whether the trajectories in the test set also appear fully or partially in the training set. We consistently discover a severe problem of trajectory overlapping in all analyzed datasets, highlighting that predictors memorize trajectories while having limited generalization capacities. We thus propose a methodology to rerank the outputs of the next-location predictors based on spatial mobility patterns. With these techniques, we significantly improve the predictors' generalization capability, with a relative improvement on the accuracy up to 96.15% on the trajectories that cannot be memorized (i.e., low overlap with the training set).