Metraipolis › archive › dc_32705c04dcfa
What Personal Information Improves LLM-Based Next-Location Prediction? — arXiv:2609.09609
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.09609
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T07:54:15.532Z
- SHA-256 of the archived text
1354f0db657d4f4f414e9d1657c070b50ef318c57bd888cc383539d5fd28e2a9- Stable URL of this page
https://metraipolis.com/documento/dc_32705c04dcfa
How to cite
What Personal Information Improves LLM-Based Next-Location Prediction? — arXiv:2609.09609 — arXiv (en), https://arxiv.org/abs/2609.09609 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_32705c04dcfa (Metraipolis archive dc_32705c04dcfa, sha256 1354f0db657d4f4f414e9d1657c070b50ef318c57bd888cc383539d5fd28e2a9)
BibTeX
@misc{dc32705c04dcfa,
title = {What Personal Information Improves LLM-Based Next-Location Prediction? — arXiv:2609.09609},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.09609},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_32705c04dcfa; sha256 1354f0db657d4f4f414e9d1657c070b50ef318c57bd888cc383539d5fd28e2a9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09609. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) are increasingly used for individual next-location prediction, with personal information easily added to prompts alongside mobility history. Yet the incremental predictive value of such information remains unclear. Using linked sociodemographic records and mobility traces from 5,000 Shenzhen residents, this study separates model responsiveness from predictive value. GPT-5 is the primary model, with GPT-5.5 and Claude Opus 4.6 used for replication. In 1,000 paired prediction instances, models rank 100 candidate destinations with and without age, gender, occupation and income while all other inputs are held fixed. Behavioural history raises top-1 accuracy from 5.6% to 18.5% as prior history increases from zero to six days. By contrast, sociodemographic attributes produce no detectable overall gain, although replacing correct attributes with those of another person reduces accuracy by 5.4 percentage points. Candidate construction also matters, removing distance raises accuracy by 7.7 points under proximity sampling but lowers it by 22.3 points under popularity sampling, with the reversal reproduced across all three LLMs. These findings identify behavioural history as the clearest source of incremental value and show that personal information should be evaluated under matched, explicitly specified conditions before its privacy and governance costs are justified. Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-09-10 in cs.CY). Categorie arXiv: Computers and Society (cs.CY). Pagina del lavoro: https://arxiv.org/abs/2609.09609 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T07:30:36.965Z dalla pagina https://arxiv.org/catchup/cs.CY/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).