Time Series Foundation Models are Flow Predictors
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data
Human experts typically integrate numerical and textual multimodal information to analyze time series. However, most traditional deep learning predictors rely solely on unimodal numerical data, using a fixed-length windo…
Language ModelingLanguage ModellingLarge Language ModelTime Series+1Prediction of Dynamical time Series Using Kernel Based Regression and Smooth Splines
Prediction of dynamical time series with additive noise using support vector machines or kernel based regression has been proved to be consistent for certain classes of discrete dynamical systems. Consistency implies tha…
DenoisingregressionTime SeriesTime Series AnalysisSundial: A Family of Highly Capable Time Series Foundation Models
We introduce Sundial, a family of native, flexible, and scalable time series foundation models. To predict the next-patch's distribution, we propose a TimeFlow Loss based on flow-matching, which facilitates native pre-tr…
Representation LearningTime SeriesTime series features for supporting hydrometeorological explorations and predictions in ungauged locations using large datasets
Regression-based frameworks for streamflow regionalization are built around catchment attributes that traditionally originate from catchment hydrology, flood frequency analysis and their interplay. In this work, we devia…
regressionTime SeriesTime Series AnalysisCadence: Error-Bounded Lossy Compression of Demand Time Series with a Time-Series Foundation Model
We present Cadence, an error-bounded lossy compressor for numeric time series pairing a 330M-parameter time-series foundation model (Google TimesFM-3) with an adaptive arithmetic coder, guaranteeing |x_t-x_t|leτ on every…