本文介绍4种时序任务（长期/短期预测、插值、分类、异常检测）常用的时间序列数据集。
| Tasks | Benchmarks | Metrics | Series Length |
|---|---|---|---|
| Long-term Forecasting | ETT (4 subsets), Electricity, Traffic, Weather, Exchange, ILI | MSE, MAE | 96~720 (ILI: 24∼60) |
| Short-term Forecasting | M4 (6 subsets) | SMAPE, MASE, OWA | 6~48 |
| Imputation | ETT (4 subsets), Electricity, Weather | MSE, MAE | 96 |
| Classification | UEA (10 subsets) | Accuracy | 29∼1751 |
| Anomaly Detection | SMD, MSL, SMAP, SWaT, PSM | Precision, Recall, F1-Socre | 100 |
WIP
《时间序列任务数据集简介》有1条评论