Selecting Algorithms

Select the algorithms to use for the advanced prediction.

To define the algorithm to use for the advanced prediction:

  1. In the Select Algorithms section, select the algorithm to use:

    • Oracle AutoMLx—A proprietary suite of ten algorithms (including both univariate and multivariate); automatically selects the best model for the given error measure. Runs all of these algorithms and selects the best option with the best results for you.

      • Runs various statistical models and machine learning algorithms on your data.
      • Tunes and validates the models.
      • Finds the best model for your data.
      • Fits your data to the best model.

    • Light GBM—Light Gradient Boosting, an ensemble- and tree-based, speed efficient algorithm suited for larger data sets. Best suited for data sets where time has less weight as compared to other features.

    • XGBoost—Extreme Gradient Boosting, an ensemble- and tree-based algorithm, best suited for data sets where time has less weight as compared to other features.

    • Prophet—Time series algorithm best suited for data with strong seasonal effects and several seasons of historical data.

    • SARIMAX—Arima with exogeneous algorithms.

  2. Select the Forecast Error Metric to use for the selected algorithm to define how the algorithm should select the best model. It optimizes the model training based on the selected error metric to determine the best option to use for the prediction. The ML engine learns the patterns from the data, and looks for the best option to minimize errors to the extent possible. The ML engine evaluates each iteration against the error metric you select, and selects the iteration when the error metric is the lowest.
    • sMAPE—Symmetric Mean Absolute Percentage Error
    • MAPE—Mean Absolute Percentage Error
    • RMSE—Root Mean Squared Error

    Using your choice of error measure, Advanced Predictions:

    • Chooses the model with the least error as the best model.
    • For the best model:
      • Generates fitted series corresponding to the input series.
      • Generates forecast for the horizon.