SOTAVerified

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

Showing 351–400 of 1609 papers

TitleStatusHype
Discovering Predictable Latent Factors for Time Series ForecastingCode1
Graph Neural Controlled Differential Equations for Traffic ForecastingCode1
HDT: Hierarchical Discrete Transformer for Multivariate Time Series ForecastingCode1
Multi-Scale Adaptive Graph Neural Network for Multivariate Time Series ForecastingCode1
Disentangling Long-Short Term State Under Unknown Interventions for Online Time Series ForecastingCode1
Multivariate Probabilistic Time Series Forecasting with Correlated ErrorsCode1
Multi-Variate Time Series Forecasting on Variable SubsetsCode1
Multivariate Time Series Forecasting with Dynamic Graph Neural ODEsCode1
A spatio-temporal LSTM model to forecast across multiple temporal and spatial scalesCode1
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic ForecastingCode1
Adaptive Graph Convolutional Recurrent Network for Traffic ForecastingCode1
Discrete Graph Structure Learning for Forecasting Multiple Time SeriesCode1
Graph-based Multi-ODE Neural Networks for Spatio-Temporal Traffic ForecastingCode1
A Multi-view Multi-task Learning Framework for Multi-variate Time Series ForecastingCode1
Instance-wise Graph-based Framework for Multivariate Time Series ForecastingCode1
Learning the Evolutionary and Multi-scale Graph Structure for Multivariate Time Series ForecastingCode1
Gateformer: Advancing Multivariate Time Series Forecasting through Temporal and Variate-Wise Attention with Gated RepresentationsCode1
GBT: Two-stage transformer framework for non-stationary time series forecastingCode1
Time series forecasting with Gaussian Processes needs priorsCode1
FreqMoE: Enhancing Time Series Forecasting through Frequency Decomposition Mixture of ExpertsCode1
Generative Pretrained Hierarchical Transformer for Time Series ForecastingCode1
FrAug: Frequency Domain Augmentation for Time Series ForecastingCode1
Practical Forecasting of Cryptocoins Timeseries using Correlation PatternsCode1
Prediction of the Position of External Markers Using a Recurrent Neural Network Trained With Unbiased Online Recurrent Optimization for Safe Lung Cancer RadiotherapyCode1
ForecastNet: A Time-Variant Deep Feed-Forward Neural Network Architecture for Multi-Step-Ahead Time-Series ForecastingCode1
Diffusion Auto-regressive Transformer for Effective Self-supervised Time Series ForecastingCode1
ForecastPFN: Synthetically-Trained Zero-Shot ForecastingCode1
FreEformer: Frequency Enhanced Transformer for Multivariate Time Series ForecastingCode1
Deep Switching Auto-Regressive Factorization:Application to Time Series ForecastingCode1
Deep Switching State Space Model (DS^3M) for Nonlinear Time Series Forecasting with Regime SwitchingCode1
FlexTSF: A Universal Forecasting Model for Time Series with Variable RegularitiesCode1
Multi-modal learning for geospatial vegetation forecastingCode1
CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial CorrelationsCode1
First De-Trend then Attend: Rethinking Attention for Time-Series ForecastingCode1
Forecasting with Deep LearningCode1
CMamba: Channel Correlation Enhanced State Space Models for Multivariate Time Series ForecastingCode1
Financial time series forecasting with multi-modality graph neural networkCode1
Radflow: A Recurrent, Aggregated, and Decomposable Model for Networks of Time SeriesCode1
auto-sktime: Automated Time Series ForecastingCode1
Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series ForecastingCode1
Client: Cross-variable Linear Integrated Enhanced Transformer for Multivariate Long-Term Time Series ForecastingCode1
DEPTS: Deep Expansion Learning for Periodic Time Series ForecastingCode1
Forecasting with Hyper-TreesCode1
Federated Learning for 5G Base Station Traffic ForecastingCode1
Few-Shot Forecasting of Time-Series with Heterogeneous ChannelsCode1
Revisiting Attention for Multivariate Time Series ForecastingCode1
FDNet: Focal Decomposed Network for Efficient, Robust and Practical Time Series ForecastingCode1
Risk and cross validation in ridge regression with correlated samplesCode1
FC-GAGA: Fully Connected Gated Graph Architecture for Spatio-Temporal Traffic ForecastingCode1
FECAM: Frequency Enhanced Channel Attention Mechanism for Time Series ForecastingCode1
Show:102550
← PrevPage 8 of 33Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1InformerMSE0.88—Unverified
2QuerySelectorMSE0.85—Unverified
3TransformerMSE0.83—Unverified
4AarenMSE0.65—Unverified
5RPMixerMSE0.52—Unverified
6ATFNetMSE0.51—Unverified
7MOIRAILargeMSE0.51—Unverified
8AutoformerMSE0.51—Unverified
9SCINetMSE0.5—Unverified
10S-MambaMSE0.49—Unverified
#ModelMetricClaimedVerifiedStatus
1QuerySelectorMSE1.12—Unverified
2TransformerMSE1.11—Unverified
3InformerMSE0.94—Unverified
4GLinearMSE0.59—Unverified
5SCINetMSE0.54—Unverified
6MoLE-DLinearMSE0.51—Unverified
7PRformerMSE0.49—Unverified
8TEFNMSE0.48—Unverified
9DLinearMSE0.47—Unverified
10FiLMMSE0.47—Unverified
#ModelMetricClaimedVerifiedStatus
1TransformerMSE2.66—Unverified
2QuerySelectorMSE2.32—Unverified
3InformerMSE1.67—Unverified
4DLinearMSE0.45—Unverified
5TEFNMSE0.42—Unverified
6MoLE-DLinearMSE0.42—Unverified
7FiLMMSE0.38—Unverified
8MoLE-RLinearMSE0.37—Unverified
9SCINetMSE0.37—Unverified
10PRformerMSE0.36—Unverified
#ModelMetricClaimedVerifiedStatus
1TransformerMSE3.18—Unverified
2QuerySelectorMSE3.07—Unverified
3InformerMSE2.34—Unverified
4MoLE-DLinearMSE0.61—Unverified
5DLinearMSE0.61—Unverified
6SCINetMSE0.48—Unverified
7FiLMMSE0.44—Unverified
8TEFNMSE0.43—Unverified
9TiDEMSE0.42—Unverified
10MoLE-RLinearMSE0.41—Unverified
#ModelMetricClaimedVerifiedStatus
1MoLE-DLinearMSE0.45—Unverified
2TEFNMSE0.43—Unverified
3FiLMMSE0.41—Unverified
4PatchTST/64MSE0.41—Unverified
5TiDEMSE0.41—Unverified
6NLinearMSE0.41—Unverified
7DiPE-LinearMSE0.41—Unverified
8DLinearMSE0.41—Unverified
9RLinearMSE0.4—Unverified
10MoLE-RLinearMSE0.4—Unverified
#ModelMetricClaimedVerifiedStatus
1DLinearMSE0.38—Unverified
2TEFNMSE0.38—Unverified
3MoLE-DLinearMSE0.36—Unverified
4FiLMMSE0.36—Unverified
5NLinearMSE0.34—Unverified
6PatchTST/64MSE0.34—Unverified
7MoLE-RLinearMSE0.34—Unverified
8TiDEMSE0.33—Unverified
9PRformerMSE0.33—Unverified
10LTBoost (drop_last=false)MSE0.33—Unverified
#ModelMetricClaimedVerifiedStatus
1DLinearMSE0.29—Unverified
2TEFNMSE0.29—Unverified
3MoLE-DLinearMSE0.29—Unverified
4FiLMMSE0.28—Unverified
5NLinearMSE0.28—Unverified
6TSMixerMSE0.28—Unverified
7DiPE-LinearMSE0.28—Unverified
8PatchTST/64MSE0.27—Unverified
9MoLE-RLinearMSE0.27—Unverified
10TiDEMSE0.27—Unverified
#ModelMetricClaimedVerifiedStatus
1TEFNMSE0.38—Unverified
2MoLE-DLinearMSE0.38—Unverified
3TiDEMSE0.38—Unverified
4MoLE-RLinearMSE0.38—Unverified
5FiLMMSE0.37—Unverified
6PatchTST/64MSE0.37—Unverified
7DiPE-LinearMSE0.37—Unverified
8TSMixerMSE0.37—Unverified
9RLinearMSE0.37—Unverified
10TTMMSE0.36—Unverified
#ModelMetricClaimedVerifiedStatus
1TEFNMSE0.23—Unverified
2DLinearMSE0.22—Unverified