M4
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
M4 hourly
13.090.9-Risk Accuracy
6
M4-multilingual (test)
93.42Avg Recall
6
M4 monolingual (test)
98.44Avg Recall
6
M4 Monthly
0.25MSE
5
M4 Average
11.36SMAPE
5
M4 Monthly M-competition
0.092sCRPS
5
M4 (out-of-domain)
76.12Accuracy
5
M4 Hourly
0.223MSE
5
M4 Average (Total)
1.511MASE
5
M4 Hourly
0.893MASE
5
M4 Average Competition (100k)
11.291sMAPE
5
M4 hourly
0.179NRMSE
4
M4 (macro)
84.5Balanced Accuracy
4
M4 (test)
61.5Accuracy (Human Judgements)
4
M4
57.6ArXiv pAUC@1
4
M4 caption (test)
0.114BLEU@4
4
M4 Quarterly
10.1SMAPE
3
M4 Yearly
13.7SMAPE
3
M4 Y-o-Y Sales Growth
7.1Coverage Delta
3
M4 Aggregated Sales
10.4Coverage Delta
3
M4 Raw Sales
6.9Coverage Delta
3
M4
2.49ASR
3
M4 (test)
97.33Accuracy
3
M4 Hourly horizon 48
0.011WQL
3
M4 H GluonTS (test)
3.4412-Wasserstein distance
2