Time Series Forecasting

Latest papers 667

139 papers in the last four weeks, up 101% on the four weeks before. 0.9% of all new papers.

How Good Are Time-Series Foundation Models for Pedestrian Crowd Count Forecasting? A Cross-Dataset Comparative Study
Sep 14, 2026Theivaprakasham Hari, Ziteng Li, Yanan Xin +2Crowd Counting Time Series Forecasting
Department of Transport & Planning, Faculty of Civil Engineering and Geosciences, Delft University of Technology, 2628 CN Delft, The Netherlands
Parameter-Efficient Adaptation of Pretrained Language Models for Time-Series Forecasting
Sep 14, 2026Tamanna Kumavat, Georg Brunner, Kyriakos FlourisTime Series Forecasting LLM-Based Time Series Forecasting
University of Zurich, Switzerland · Computer Vision Laboratory, ETH Zurich, Switzerland · MRC Biostatistics Unit, University of Cambridge, United Kingdom
Beyond Numerical Time Series: A Unified Benchmark for Multimodal Forecasting with Heterogeneous Context
Sep 14, 2026Peng Chen, Zhihao Zhuang, Hongzhou Chen +6Multivariate Time Series Forecasting Time Series Forecasting
Ant International · Hangzhou, China
WaVeFuse: Regime-Adaptive Equity Index Forecasting via Channel-Wise Wavelet Denoising and Vertical Attention Fusion
Sep 13, 2026Aashish Bohra, Vivek VijayTime Series Forecasting Financial Time Series
Department of Computer Science and Engineering, Indian Institute of Technology Jodhpur, Jodhpur, Rajasthan, India
Are Gradient Boosting Models Suitable for Intermittent Demand Forecasting?
Sep 13, 2026Vladislav Kislinskii, Mazhar HameedTime Series Forecasting Gradient-Boosted Decision Trees
Gisma University of Applied Sciences, Potsdam, Germany
Real-World Deployment and Performance Characterisation of Fog-Based Deep Learning for Cold-Chain Temperature Prediction over LoRaWAN
Sep 12, 2026Jeremiah Taguta, Jean Frederic Isingizwe Nturambirwe, Clement Nthambazale NyirendaTime Series Forecasting Edge Computing
Department of Computer Science University of the Western Cape Cape Town, South Africa · eResearch Office University of the Western Cape Cape Town, South Africa
Phorecaster365: A Human-Supervised Reference Architecture for Hybrid Pharmaceutical Sales Forecasting and Planning Decision Support
Sep 12, 2026Houman Kazemzadeh, Kamyar NaderiTime Series Forecasting
Izlek Technology, Ankara, Türkiye · Xylemed, Dubai, United Arab Emirates
Accuracy Is Not Service: A Decision-Aware Benchmark for Intermittent-Demand Forecasting
Sep 12, 2026Joo Ern Chin, Shih-Fen Cheng, Aldy GunawanTime Series Forecasting Forecasting Benchmarks
School of Computing and Information Systems, Singapore Management University 80 Stamford Road, Singapore 178902 · ST Logistics Pte. Ltd. 5 Clementi Loop, Singapore 129816
PPDL: A Real-world Industrial User Retention Ratio Forecasting Framework Integrating Physical Priors with Deep Learning
Sep 12, 2026Zibo Zhao, Zhengxiong Guan, Chaoli Zhang +4Time Series Forecasting Human Behavior Prediction
Zhejiang Normal University · Douyin Group · Shanghai Jiao Tong University
A Hybrid LSTM-XGBoost Framework for Multi-Horizon Stock Return Prediction Across Diversified Equity Portfolios
Sep 11, 2026Seif ElDein Mostafa, Yahia Ahmed, Farah Datwish +1Financial Forecasting Time Series Forecasting
Faculty of Computer Science MSA University Giza, Egypt
Explaining Time Series Forecasting with Horizon-Resolved Attribution
Sep 11, 2026Seunghan Lee, Jun Seo, Jaehoon Lee +9Explainable Time Series Forecasting Feature Attribution
LG AI Research
Observation-Anchored Selective Assimilation for Longitudinal Tumor-State Proxy Forecasting in Post-Treatment Glioma
Sep 11, 2026Yeonjae Jung, Minwoo ShinTime Series Forecasting Longitudinal Medical Image Analysis
Department of Software, Yonsei University, Wonju, 26493, Republic of Korea
Context-Aware Causal Gaze Forecasting for Human-Vehicle Interaction During In-Cabin Tracking Dropouts
Sep 11, 2026Shabnam Shabani, Ghazal FarhaniGaze Estimation Time Series Forecasting
Department of Computer Science Western University London, ON, Canada · National Research Council Canada London, ON, Canada
LoRA-RC: Reservoir Computing with Low-Rank Adaptation
Sep 11, 2026Wenbin WanDynamical Systems Time Series Forecasting
Department of Mechanical Engineering, University of New Mexico, Albuquerque, NM 87131, USA
Making Alternative Data Work: Context-Augmented LLMs for Financial Forecasting
Sep 10, 2026Jihoon Kwon, Lawrence Liu, Daekyung Park +15Financial Forecasting Time Series Forecasting
LinqAlpha · Carbon Arc · Kalshi +7
Predicting Train Delays in Finland Using Machine Learning and Weather Data
Sep 10, 2026Vinicius Pozzobon Borin, Jean Michel de Souza Sant'Ana, Nurul Huda MahmoodIntelligent Transportation Systems Time Series Forecasting
Centre for Wireless Communications, University of Oulu, Oulu, Finland
CryptoL: Towards Scale Dominance and Physics Constraints Mitigation in Financial Multivariate Time Series Forecasting
Sep 10, 2026Yalda Taheri, Mohammad Hassan Heydari, Armon Rasooli +3Multivariate Time Series Forecasting Financial Forecasting
Faculty of Engineering, Azad University · Faculty of Computer Engineering, University of Isfahan · Department of Electrical Engineering, Iran University of Science and Technology
Loading history and window geometry bound compact-state slip ranking during granular shear startup
Sep 9, 2026Ruixin Zhou, Boliang YuMaterials Science Time Series Forecasting
School of Physics and Astronomy, Shanghai Jiao Tong University, Shanghai 200240, China
Multi-Task Learning for Sparsely-Labeled Time Series: A Case Study on Cold-Hardiness Modeling
Sep 8, 2026Aseem Saxena, Paola Pesántez-Cabrera, Markus Keller +1Time Series Forecasting Multi-Task Learning
School of Electrical Engineering and Computer Science, Oregon State University, Corvallis, 97331, OR, USA. · School of Electrical Engineering and Computer Science, Washington State University, Pullman, 99163, WA, USA. · Irrigated Agriculture Research and Extension Center, Washington State University, Prosser, 99350, WA, USA.
Nyström Attention Matches Full Attention for Cross-Sectional Stock Prediction
Sep 8, 2026Kunhan GuoLow-Rank Attention Financial Forecasting
The University of Hong Kong
A Multimodal Label Forecasting Method for Aperiodic Visuo-Motor Time Series
Sep 7, 2026Borui He, Garrett E KatzMultivariate Time Series Forecasting Time Series Forecasting
EECS Department, Syracuse University, Syracuse NY 13244, USA.
Decomposition-Guided Diffusion Language Models for Inertial Confinement Fusion Prediction
Sep 7, 2026Xiang Zhang, Varchas Gopalaswamy, Rahman Ejaz +2Time Series Forecasting Physics-Informed ML
Purdue University · University of Rochester
EXAONE Forecast for Finance
Sep 7, 2026Seunghan Lee, Jaehoon Lee, Jun Seo +9Multivariate Time Series Forecasting Financial Forecasting
LG AI Research∗
Halo: Improving forecast accuracy through heteroscedastic estimation
Sep 6, 2026Adam CataldoTime Series Forecasting Heteroscedastic Regression
AI Quant Researcher
Assessing Covariate-Informed Grid Load Forecasting with a Time-Series Foundation Model
Sep 6, 2026Varsha Pendyala, Yiwei Fu, Weizhong Yan +1Electricity Load Forecasting Time Series Forecasting
Artificial Intelligence Team GE Vernova Advanced Research Center, Niskayuna, NY, USA
Role-Specific Predictive Geometries for Nonstationary Multivariate Graph-Signal Forecasting
Sep 6, 2026Yanbo Chen, Anamitra MakurTime Series Forecasting Multivariate Time Series Forecasting
School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore
Predictors and Orchestrators: Parsimonious Machine Learning within an Agentic AI Harness for Multi-Horizon Karst Aquifer Forecasting
Sep 6, 2026Pramod Lekhak, Chetan Sharma, Hakan Başağaoğlu +2Time Series Forecasting Spatiotemporal Forecasting
School of Civil and Environmental Engineering & Construction Management, University of Texas at San Antonio, San Antonio, TX 78249, USA · Civil Engineering Department, Jodhpur Institute of Engineering and Technology, Jodhpur-342802, Rajasthan, India · Edwards Aquifer Authority, 900 E. Quincy St., San Antonio, TX 78215, USA
Predicting Wind Turbine Power Using Machine Learning and Weather Forecasts
Sep 5, 2026Khivishta Boodhoo, Isaac Triguero, Josh Plumbly +2Wind Power Forecasting Time Series Forecasting
Low Carbon Energy and Resources Technologies Research Group, Faculty of Engineering, University of Nottingham. · Computational Optimisation and Learning Lab, School of Computer Science, University of Nottingham, Nottingham, United Kingdom · Department of Computer science and Artificial Intelligence,University of Granada, Spain +3
How Faithful Is Attribution for Sales Forecasting? A Counterfactual Study
Sep 4, 2026Glib KechynExplainable Time Series Forecasting Feature Attribution
Beyond a Universal Forecasting Selector: Demand-Conditioned Model Selection across Demand Patterns and Horizons
Sep 3, 2026Adolfo GonzálezModel Selection Time Series Forecasting
Department of Computer Engineering and Informatics, Faculty of Engineering, University of Santiago of Chile, Santiago, Chile

Sep 14, 2026, cs.LGJ/K move · Enter open · S save

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

Theivaprakasham Hari, Ziteng Li, Yanan Xin, Winnie Daamen+1

Department of Transport & Planning, Faculty of Civil Engineering and Geosciences, Delft University of Technology, 2628 CN Delft, The Netherlands

Crowd Counting Time Series Forecasting Forecasting Benchmarks Time-Series Foundation Models

Open paper AskPDF arXiv

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.