The paper critiques the prevalent use of mean squared error (MSE) for evaluating irregular time‑series forecasting, arguing that MSE is biased by timestamp sampling distributions. It introduces the Continuous‑time Squared Error (CSE), an importance‑weighted metric that theoretically offers a tighter asymptotic bound on continuous‑time risk than MSE. A comprehensive benchmark across synthetic, semi‑synthetic, and eight real‑world datasets demonstrates that CSE more accurately recovers continuous‑time risk, revealing limitations of relying solely on MSE.
By Rongwen Li, Haixin Xie, Xiao Wang, Changjian Chen
Existing research on irregular time-series forecasting has primarily focused on model design, while evaluation metrics remain insufficiently studied. Existing benchmarks typically use mean squared error (MSE) as the evaluation metric.
arXiv:2609.16415v1 Announce Type: cross
Abstract: Pedestrian-count forecasting supports pedestrian-oriented Intelligent Transportation Systems (ITS), including crowd monitoring, pedestrian-traffic st...
By Theivaprakasham Hari, Ziteng Li, Yanan Xin, Winnie Daamen, Serge Hoogendoorn
arXiv:2602. 16224v2 Announce Type: replace Abstract: Time series data are prone to noise in various domains, and training samples may contain low-predictability patterns that deviate from the normal data distribution, leading to training instability or convergence to poor local minima.
By Xu Zhang, Peng Wang, Yichen Li, Wei Wang
arXiv:2606. 18367v1 Announce Type: new Abstract: Standard benchmarks evaluate time series foundation models (TSFMs) using aggregate metrics, but these can mask severe failures in critical operating regimes.
By Yingshuo Wang, Xian Sun, Lingdong Kong, Wei Gao, Yanhang Li, Zhichao Fan, Zexin Zhuang
The paper introduces Generalized Gibbs Ensemble Weighting (GGEW), a probabilistic framework that assigns weights to forecasting models using a Gibbs-style exponential transformation of normalized predictive loss. GGEW extends basic weighting through numerical stabilization, diversity-aware score corrections, and online hyperparameter adaptation, yielding variants such as Stable Gibbs weighting, Directional Gibbs-NCL, and Symmetric Gibbs-NCL. The authors evaluate GGEW on M4 competition submissions and real-world datasets (Monash Traffic, Electricity, Solar), finding that Gibbs-style adaptive weighting is competitive across various settings, though performance varies by dataset, horizon, and deployment protocol.
By Prasen R. Nuthanakaluva, Nava K. Gaddam
Aurora‑X is a billion‑parameter time‑series foundation model designed for extreme forecasting tasks. It employs a progressive curriculum that starts with channel‑independent pretraining, then adds cross‑variable dependencies, variable context and horizon lengths, and optional future covariates during mid‑training. A variable‑resolution post‑training stage allows adjustable temporal spans per token at inference, while a pattern‑guided mixture‑of‑experts expands capacity through sparse activation and expert specialization. An implicit quantile network head predicts arbitrary quantiles, enhancing probabilistic forecasting flexibility. Experiments on GIFT‑Eval, TIME, FEV‑Bench, TFB, and DAG‑Bench show state‑of‑the‑art performance against both pretrained TSFMs and task‑specific supervised models.
By Xingjian Wu, Chenjuan Guo, Xiangfei Qiu, Zhigang Hu, Hanyin Cheng, Peng Chen, Yang Shu, Jilin Hu, Bin Yang
The paper proposes a proactive approach to road safety in Greater Sydney by using connected vehicle telemetry to predict risky driving events before crashes occur. It quantifies risky driving with g‑force thresholds and builds spatio‑temporal heatmaps to locate high‑risk zones. Eight predictive models were compared, with ARIMA achieving the lowest error and showing that simple time‑series methods can rival deep learning when data are limited, highlighting the value of IoT data for targeted safety interventions.
By Adriana-Simona Mih\u{a}i\c{t}\u{a}, Clarence Cheung, Artur Grigorev, Tuo Mao, David Lillo-Trynes
arXiv:2606. 27282v1 Announce Type: new Abstract: Time-series forecasting research has been moving steadily toward larger architectures, from specialized transformers to general-purpose foundation models, on the assumption that capacity is what unlocks accuracy.
By Lang Huang, Jinglue Xu, Luke Darlow
arXiv:2609.39386v1 Announce Type: new
Abstract: Pretrained time-series foundation models (TSFMs) are evaluated as forecasters of future values, yet for sparse series many decisions depend only on whi...
By Daniel Schoess, Florian von Wangenheim
arXiv:2608. 14106v1 Announce Type: cross Abstract: When forecasting hourly returns for 1,000 US equities, we observe an unexpected phenomenon: predictions become nearly flat and show poor stock ranking, as measured by cross-sectional correlation.
By Shu Wan, Miles Ma, Hank Zhu, Guangqi Liu, Stephen Wang, Qingsong Wen, Huan Liu
arXiv:2607. 05450v1 Announce Type: cross Abstract: This paper explores the "Granularity Paradox" in time-series forecasting, wherein finer temporal disaggregation (e.
By Hugo Moreira