{"ID":2899744,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.00945","arxiv_id":"2507.00945","title":"Time Series Foundation Models are Flow Predictors","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.","short_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 evol...","url_abs":"https://arxiv.org/abs/2507.00945","url_pdf":"https://arxiv.org/pdf/2507.00945v1","authors":"[\"Massimiliano Luca\",\"Ciro Beneduce\",\"Bruno Lepri\"]","published":"2025-07-01T16:51:16Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.CY\"]","methods":"[]","has_code":false}