Metraipolis › archive › dc_6a4e665f3115

How Good Are Time-Series Foundation Models for Pedestrian Crowd Count Forecasting? A Cross-Dataset Comparative Study — arXiv:2609.16415

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.16415
License (as archived)
CC0-1.0
Archived
2026-10-15T18:34:53.928Z
SHA-256 of the archived text
c94961d6b4c59a1c2a1568da98e19a0aa5efbfe024336a5fe35cb4ed3d0986ae
Stable URL of this page
https://metraipolis.com/documento/dc_6a4e665f3115

How to cite

How Good Are Time-Series Foundation Models for Pedestrian Crowd Count Forecasting? A Cross-Dataset Comparative Study — arXiv:2609.16415 — arXiv (en), https://arxiv.org/abs/2609.16415 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6a4e665f3115 (Metraipolis archive dc_6a4e665f3115, sha256 c94961d6b4c59a1c2a1568da98e19a0aa5efbfe024336a5fe35cb4ed3d0986ae)
BibTeX
@misc{dc6a4e665f3115,
  title = {How Good Are Time-Series Foundation Models for Pedestrian Crowd Count Forecasting? A Cross-Dataset Comparative Study — arXiv:2609.16415},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.16415},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6a4e665f3115; sha256 c94961d6b4c59a1c2a1568da98e19a0aa5efbfe024336a5fe35cb4ed3d0986ae},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16415. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pedestrian-count forecasting supports pedestrian-oriented Intelligent Transportation Systems (ITS), including crowd monitoring, pedestrian-traffic staffing and routing, and proactive risk mitigation during surges. Recent time-series foundation models (FMs) report strong zero-shot accuracy on heterogeneous forecasting benchmarks, but it remains unclear whether these gains transfer reliably to pedestrian sensing deployments. We benchmark seven univariate forecasting approaches spanning four paradigms: Seasonal Naive, gradient-boosted trees (LightGBM, CatBoost), deep learning models (N-HiTS, PatchTST), and two pretrained FMs (TimesFM, Chronos-2). Experiments cover two complementary regimes: (i) a five-day special event dataset SAIL2025 at 3-minute resolution with limited in-domain history; and (ii) Melbourne pedestrian sensors as a multi-year hourly dataset (2010--2017) with strong seasonality. We compare the MAE and RMSE results per sensor across datasets and multiple forecast horizons. Results show three consistent findings. First, with limited historical data, Seasonal Naive remains a strong baseline for long-horizon forecasting on high-volume sensors, while trained models can degrade when the next day differs substantially from prior days. Second, boosted trees can be competitive on lower-volume sensors but exhibit higher sensitivity on high-volume sensors under event-driven shift. Third, FMs excel in the seasonal and data-rich regime under long-context configuration. The findings highlight the importance of choosing pedestrian forecasting models based on both the underlying data conditions and the forecasting horizon.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.16415 — 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 2026-10-15T18:03:09.636Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).