List your company
ResearchFormerly WizWand

Time Series Forecasting on ETTh2 (5% train)

0.265MSESSDA
0.117361.113932.11053.10707Nov 29, 2025Dec 26, 2025Jan 22, 2026Feb 18, 2026Mar 17, 2026Apr 13, 2026May 10, 2026
Updated 5mo ago

Evaluation results

MethodLinks
SSDAforecast_horizon=96, training_data_ratio=5%2026.050.2650.325
VisionTSforecast_horizon=96, training_data_ratio=5%2026.050.30.337
Time-VLMforecast_horizon=96, training_data_ratio=5%2026.050.3020.365
SSDARatio=5%2026.050.3110.358
Time-LLMforecast_horizon=96, training_data_ratio=5%2026.050.3360.397
FiCoTSInput sequence length=512, Predictive lengths={96, 192, 336, 720}, Training data ratio=5%, Method category=LLM-based2025.110.3370.382
TTM + CoRAModel Category=Pre-trained, Plugin=CoRA2026.030.34—
TTMModel Category=Pre-trained, Plugin=None2026.030.343—
VisionTSRatio=5%2026.050.3480.376
SSDAforecast_horizon=336, training_data_ratio=5%2026.050.3490.385
Timer + CoRAModel Category=Pre-trained, Plugin=CoRA2026.030.35—
TimeVLMInput sequence length=512, Predictive lengths={96, 192, 336, 720}, Training data ratio=5%, Method category=LLM-based2025.110.3540.402
Time-VLMRatio=5%2026.050.3540.402
TimerModel Category=Pre-trained, Plugin=None2026.030.356—
GPT4TS + CoRAModel Category=LLM-based, Plugin=CoRA2026.030.362—
Moment + CoRAModel Category=Pre-trained, Plugin=CoRA2026.030.365—
CALF + CoRAModel Category=LLM-based, Plugin=CoRA2026.030.367—
MomentModel Category=Pre-trained, Plugin=None2026.030.37—
CALFModel Category=LLM-based, Plugin=None2026.030.373—
GPT4TSModel Category=LLM-based, Plugin=None2026.030.375—
GPT4TSforecast_horizon=96, training_data_ratio=5%2026.050.3760.421
VisionTSforecast_horizon=336, training_data_ratio=5%2026.050.3790.402
S^2IP-LLMInput sequence length=512, Predictive lengths={96, 192, 336, 720}, Training data ratio=5%, Method category=LLM-based2025.110.380.413
Time-LLMRatio=5%2026.050.3820.418
UniTime + CoRAModel Category=LLM-based, Plugin=CoRA2026.030.386—
TIME-LLMParameters (M)=6.46, Memory (MiB)=3907, Eff.*MSE=0.39, Eff.*MAE=0.38, Few-shot (5% data)=true2026.030.390.42
FEDformerforecast_horizon=96, training_data_ratio=5%2026.050.390.424
TimeLLMInput sequence length=512, Predictive lengths={96, 192, 336, 720}, Training data ratio=5%, Method category=LLM-based2025.110.3980.426
Time-VLMforecast_horizon=336, training_data_ratio=5%2026.050.3980.434
UniTimeModel Category=LLM-based, Plugin=None2026.030.399—
GPT4TSInput sequence length=512, Predictive lengths={96, 192, 336, 720}, Training data ratio=5%, Method category=LLM-based2025.110.40.433
GPT4TSParameters (M)=11.7, Memory (MiB)=371.0, Eff.*MSE=0.20, Eff.*MAE=0.20, Few-shot (5% data)=true2026.030.40.43
GPT4TSRatio=5%2026.050.40.433
PatchTSTforecast_horizon=96, training_data_ratio=5%2026.050.4010.421
Time-LLMforecast_horizon=336, training_data_ratio=5%2026.050.4050.432
GPT4TSforecast_horizon=336, training_data_ratio=5%2026.050.4080.439
TimesNetforecast_horizon=96, training_data_ratio=5%2026.050.4090.42
TimesNetInput sequence length=512, Predictive lengths={96, 192, 336, 720}, Training data ratio=5%, Method category=Non-Transformer-based2025.110.4390.448
TimesNetRatio=5%2026.050.4390.448
EFDformerParameters (M)=16.8, Memory (MiB)=87.8, Eff.*MSE=0.12, Eff.*MAE=0.13, Few-shot (5% data)=true2026.030.440.45
AutoformerInput sequence length=512, Predictive lengths={96, 192, 336, 720}, Training data ratio=5%, Method category=Transformer-based2025.110.4410.457
DLinearforecast_horizon=96, training_data_ratio=5%2026.050.4420.456
TimesNetParameters (M)=0.63, Memory (MiB)=2.9, Eff.*MSE=2.89, Eff.*MAE=3.39, Few-shot (5% data)=true2026.030.460.45
FEDformerInput sequence length=512, Predictive lengths={96, 192, 336, 720}, Training data ratio=5%, Method category=Transformer-based2025.110.4630.454
FEDformerRatio=5%2026.050.4630.454
PatchTSTforecast_horizon=336, training_data_ratio=5%2026.050.4640.469
TStationaryParameters (M)=2.02, Memory (MiB)=13.2, Eff.*MSE=0.84, Eff.*MAE=1.03, Few-shot (5% data)=true2026.030.470.46
AutoformerParameters (M)=10.53, Memory (MiB)=62.6, Eff.*MSE=0.18, Eff.*MAE=0.20, Few-shot (5% data)=true2026.030.470.49
FEDformerforecast_horizon=336, training_data_ratio=5%2026.050.4770.483
iTransformerInput sequence length=512, Predictive lengths={96, 192, 336, 720}, Training data ratio=5%, Method category=Transformer-based2025.110.4880.475
TimesNetforecast_horizon=336, training_data_ratio=5%2026.050.4990.479
One-for-AllParameters (M)=0.55, Memory (MiB)=2.2, Eff.*MSE=3.92, Eff.*MAE=4.17, Few-shot (5% data)=true2026.030.520.49
DLinearInput sequence length=512, Predictive lengths={96, 192, 336, 720}, Training data ratio=5%, Method category=Non-Transformer-based2025.110.6940.577
DLinearRatio=5%2026.050.6940.577
ETSformerInput sequence length=512, Predictive lengths={96, 192, 336, 720}, Training data ratio=5%, Method category=Transformer-based2025.110.8090.681
ETSformerParameters (M)=5.28, Memory (MiB)=31.4, Eff.*MSE=0.24, Eff.*MAE=0.29, Few-shot (5% data)=true2026.030.810.68
PatchTSTInput sequence length=512, Predictive lengths={96, 192, 336, 720}, Training data ratio=5%, Method category=Transformer-based2025.110.8270.615
PatchTSTRatio=5%2026.050.8270.615
DLinearforecast_horizon=336, training_data_ratio=5%2026.051.4240.849
ReformerParameters (M)=5.80, Memory (MiB)=33.4, Eff.*MSE=0.09, Eff.*MAE=0.17, Few-shot (5% data)=true2026.033.531.47
Informerforecast_horizon=96, training_data_ratio=5%2026.053.8371.508
InformerParameters (M)=11.33, Memory (MiB)=65.8, Eff.*MSE=0.04, Eff.*MAE=0.08, Few-shot (5% data)=true2026.033.921.65
InformerRatio=5%2026.053.9221.653
Informerforecast_horizon=336, training_data_ratio=5%2026.053.9561.52