Explainability details are exportable from all Forecaster algorithms except for LightGBM.

Explainability results derive from independent features within algorithms. This data helps to generate richer forecasts. ‌Common feature examples are:

  •  Marketing campaigns and promotions
  •  Inventory levels
  •  Product revenue

Explainability details also pinpoint the impact of the forecast inputs (such as related data), on prediction results. Below is an example of an electric bike company:

  • You can load a Forecaster data collection with information on historical oil prices, e-bike prices, and promotion data.
  • You can show whether ‌increased oil prices or promotions have a greater sales impact.

Not all features impact prediction results in the same way. Explainability results provide an idea about the degree of influence a single feature has on a prediction result. 

See below to review the impact of features on forecast results.

This bar chart shows explainability results.
There are eight features in this bar chart. At the top, Capacity Hours and the one-month lag of Partners have the greatest impact on results.