M-4 competition dataset
Emerging11papers using it
2019first seen
The M-4 competition dataset is a benchmark that contains a diverse collection of time series data used to evaluate the performance of forecasting methods.
Papers using M-4 competition dataset (11)
- Rethinking Nonstationarity in Time Series: A Deterministic Trend PerspectiveRecurrent Neural Networks for Time Series Forecasting: Current Status
and Future DirectionsTwo-Step Meta-Learning for Time-Series Forecasting EnsembleThe uncertainty estimation of feature-based forecast combinationsFor2For: Learning to forecast from forecastsHERMES: Hybrid Error-corrector Model with inclusion of External Signals
for nonstationary fashion time seriesDesigning Time-Series Models With Hypernetworks & Adversarial PortfoliosTime Series Analysis by State Space LearningTo aggregate or not to aggregate: Forecasting of finite autocorrelated
demandOptimizing accuracy and diversity: a multi-task approach to forecast
combinationsInfinite forecast combinations based on Dirichlet process