Our forecasting methods are being constantly adapted. Some of the algorithms we support include:
Statistical
- Auto-ARIMA
- ARIMA
- VARIMA
- AutoARIMA
- StatsForecastAutoARIMA
- ExponentialSmoothing
- StatsForecastAutoETS
- StatsForecastAutoCES
- BATS: Box-Cox / ARMA errors / Trend / Seasonal components
- TBATS: (Trigonometric) / Box-Cox / ARMA errors / Trend / Seasonal components
(https://robjhyndman.com/papers/ComplexSeasonality.pdf) - Theta
- FourTheta
- StatsForecastAutoTheta
- Prophet
- FFT
- KalmanForecaster
- Croston
Regression
- RegressionModel
- LinearRegressionModel
- RandomForest
- LightGBMModel
- XGBModel
- CatBoostModel
Advanced
- RNNModel
- BlockRNNModel
- NBEATSModel - Neural Basis Expansion Analysis Time Series Forecasting (N-BEATS)
(https://openreview.net/forum?id=r1ecqn4YwB) - NHiTSModel - N-HiTS: Neural Hierarchical Interpolation for Time Series Forecasting
(https://arxiv.org/abs/2201.12886) - TCNModel
- TransformerModel
- TFTModel
- DLinearModel
- NLinearModel
- TiDEModel - Time-series Dense Encoder
(http://arxiv.org/abs/2304.08424)