Contents x
    Forecast Single Strategy
    • 13 Jan 2023
    • 1 Minute to read
    • Print
    • Dark
      Light
    Contents

    Forecast Single Strategy

    • Updated on 13 Jan 2023
    • 1 Minute to read
    • Print
    • Dark
      Light
    Article summary

    Description

    The Forecast Single Strategy node applies a single forecast model to a data set, per combo split.


    Configuration Options

    Basic Configuration Options

    SettingDescription\Parameters
    Split ColumnsThe selected columns split the data set over to build additional models.
    Target ColumnThe column we are predicting.
    Sort By ColumnsSort data rows by these columns.
    Time GranularityLength of time between records in the input data set. I.e., if each input record represents a week of data, the time granularity is Week.

    Options
    • Day
    • Week
    • Month
    • Quarter
    • Year
    Role ColumnSplits the data set into scoring and training data.
    Training ValueValue in the Role Column for training data.
    Scoring ValueValue in the Role Column for scoring data.
    PredictorsThe columns we are using to predict with.
    Forecast HorizonNumber of periods to forecast forward from the end of the input data set.
    Model ColumnThe column indicates which predictive model to apply to the combo. See Forecast Strategy for a description of each model. See below for valid inputs.
    Time ColumnOptional column to seed time values for future forecast periods.
    TimeoutThe specified timeout for the action. If this time is exceeded, the node action will fail, regardless of the success of the action.

    Model Column


    ModelAllowed Model Column ValueAlternate Model Column Value
    MeanMEANFORECAST_MEAN
    ARIMAARIMAFORECAST_ARIMA
    Exponential Smoothing State SpaceETSFORECAST_ETS
    ThetaTHETAFORECAST_THETA
    Linear RegressionLINREGFORECAST_LINREG
    ProphetPROPHETFORECAST_PROPHET
    Seasonal DecompositionSTLFFORECAST_STLF
    Croston'sCROSTONFORECAST_CROSTON
    Improved Croston'sIMPROVED_CROSTONFORECAST_IMPROVED_CROSTON
    Neural NetworkNNETFORECAST_NNET
    Good Signal EnsembleGOOD_SIG_ENSFORECAST_GOOD_SIG_ENS
    Poor Signal EnsemblePOOR_SIG_ENSFORECAST_POOR_SIG_ENS
    Intermittent Data EnsembleINTER_DATA_ENSFORECAST_INTER_DATA_ENS

    Actions

    ActionDescription
    PreviewOnce any forecast models have been built, the combined result set can be previewed at any time.
    Rebuild ModelRebuild any selected models. Produces an .Rdata file that's used to forecast values.
    Was this article helpful?
    What's Next