Special days in machine learning

Special days are used by machine learning to incorporate unexpected events, such as store closures or utilities failures, in sales or volume forecasts. When training a store, the machine learning model analyzes the extent to which special days produce lower sales than normal days. Special days are incorporated into the forecast model to prevent these lower results from affecting forecasts for normal days.

When configuring special days for stores using machine learning, the Special Day Skip check box must be selected. A special day should be recorded for days when there is an unexpected closure or event with a severe negative effect on sales.

See Defining special days.