English

Time Series Foundation Models are Flow Predictors

Machine Learning 2025-07-02 v1 Computers and Society

Abstract

We investigate the effectiveness of time series foundation models (TSFMs) for crowd flow prediction, focusing on Moirai and TimesFM. Evaluated on three real-world mobility datasets-Bike NYC, Taxi Beijing, and Spanish national OD flows-these models are deployed in a strict zero-shot setting, using only the temporal evolution of each OD flow and no explicit spatial information. Moirai and TimesFM outperform both statistical and deep learning baselines, achieving up to 33% lower RMSE, 39% lower MAE and up to 49% higher CPC compared to state-of-the-art competitors. Our results highlight the practical value of TSFMs for accurate, scalable flow prediction, even in scenarios with limited annotated data or missing spatial context.

Keywords

Cite

@article{arxiv.2507.00945,
  title  = {Time Series Foundation Models are Flow Predictors},
  author = {Massimiliano Luca and Ciro Beneduce and Bruno Lepri},
  journal= {arXiv preprint arXiv:2507.00945},
  year   = {2025}
}

Comments

arXiv admin note: text overlap with arXiv:2203.07372

R2 v1 2026-07-01T03:41:56.614Z