Time Series Forecasting

Time Series Forecasting is the task of fitting a model to historical, time-stamped data in order to predict future values. Traditional approaches include moving average, exponential smoothing, and ARIMA, though models as various as RNNs, Transformers, or XGBoost can also be applied. The most popular benchmark is the ETTh1 dataset. Models are typically evaluated using the Mean Square Error (MSE) or Root Mean Square Error (RMSE).

( Image credit: ThaiBinh Nguyen )

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1–10 of 1609 papers

Title	Date	Tasks	Status	Hype
The Power of Architecture: Deep Dive into Transformer Architectures for Long-Term Time Series Forecasting	Jul 17, 2025	DecoderTime Series	CodeCode Available	0
Data Augmentation in Time Series Forecasting through Inverted Framework	Jul 15, 2025	Data AugmentationTime Series	—Unverified	0
Bridging the Last Mile of Prediction: Enhancing Time Series Forecasting with Conditional Guided Flow Matching	Jul 9, 2025	Time SeriesTime Series Forecasting	—Unverified	0
Foundation models for time series forecasting: Application in conformal prediction	Jul 9, 2025	Conformal PredictionPrediction	—Unverified	0
MoFE-Time: Mixture of Frequency Domain Experts for Time-Series Forecasting Models	Jul 9, 2025	Mixture-of-ExpertsTime Series	CodeCode Available	2
AI-Based Demand Forecasting and Load Balancing for Optimising Energy use in Healthcare Systems: A real case study	Jul 8, 2025	Demand Forecastingenergy management	—Unverified	0
Decomposing the Time Series Forecasting Pipeline: A Modular Approach for Time Series Representation, Information Extraction, and Projection	Jul 8, 2025	Computational EfficiencyTime Series	CodeCode Available	0
SEED: A Structural Encoder for Embedding-Driven Decoding in Time Series Prediction with LLMs	Jun 25, 2025	Language ModelingLanguage Modelling	—Unverified	0
A foundation model with multi-variate parallel attention to generate neuronal activity	Jun 25, 2025	Seizure DetectionTime Series	CodeCode Available	1
FAF: A Feature-Adaptive Framework for Few-Shot Time Series Forecasting	Jun 24, 2025	Meta-LearningTime Series	—Unverified	0

Show:10 25 50

← PrevPage 1 of 161Next →

All datasets ETTh1 (336) Multivariate ETTh1 (720) Multivariate ETTh2 (336) Multivariate ETTh2 (720) Multivariate ETTh1 (192) Multivariate ETTh2 (192) Multivariate ETTh2 (96) Multivariate ETTh1 (96) Multivariate Weather (192)ETTh1 (720) Univariate Weather (96)Electricity (96)

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	TEFN	MSE	0.18	—	Unverified
2	DLinear	MSE	0.18	—	Unverified
3	RLinear	MSE	0.18	—	Unverified
4	PatchTST/64	MSE	0.15	—	Unverified
5	MoLE-DLinear	MSE	0.15	—	Unverified
6	xPatch	MSE	0.15	—	Unverified
7	TSMixer	MSE	0.15	—	Unverified
8	RLinear-CI	MSE	0.15	—	Unverified
9	PRformer	MSE	0.14	—	Unverified
10	SegRNN	MSE	0.14	—	Unverified