Back to models
Forecaster

StatsForecastADIDA

API referenceSource
In-sample predictionsPrediction intervalsIn-sample prediction intervals

StatsForecast ADIDA (Aggregate-Disaggregate Intermittent Demand Approach) model.

Direct interface to statsforecast.models.ADIDA by Nixtla.

This estimator directly interfaces ADIDA, from statsforecast [1] by Nixtla.

Aggregate-Disagregate Intermittent Demand Approach: Uses temporal aggregation to reduce the number of zero observations. Once the data has been aggregated, it uses the optimized SES to generate the forecasts at the new level. It then breaks down the forecast to the original level using equal weights.

ADIDA specializes on sparse or intermittent series are series with very few non-zero observations.They are notoriously hard to forecast, and so, different methods have been developed specifically for them.

Quickstart

python
from sktime.forecasting.statsforecast import StatsForecastADIDA

estimator = StatsForecastADIDA(prediction_intervals: object | None=None)

Tags

Capabilities

  • In-sample predictions: Supported
  • Prediction intervals
  • In-sample prediction intervals: Supported
  • Categorical features: Not supported
  • Missing values: Not supported
  • Exogenous variables: Not supported
  • Multivariate: Not supported

Properties

Needs forecast horizon in fitrequires-fh-in-fit
No
X and y need the same indexX-y-must-have-same-index
Yes

Parameters(1)

prediction_intervalsConformalIntervals, optional
Information to compute conformal prediction intervals.

Examples

>>> from sktime.datasets import load_airline
>>> from sktime.forecasting.statsforecast import StatsForecastADIDA
>>> y = load_airline ()
>>> model = StatsForecastADIDA ()
>>> fitted_model = model. fit (y)
>>> y_pred = fitted_model. predict (fh = [1, 2, 3 ])

References