A seasonal pattern or correction that is applied to a normal forecast to adjust for seasonal variations. Seasonal Profiles contain multipliers for each slice of the year. Each slice's final forecast value is calculated by multiplying the base forecast value by the slice's seasonal multiplier. Seasonal profiles can be applied to bias any basic forecast. Seasonal profiles are an integral part of Winters Multiplicative demand forecasting. Each SKU forecasted with Winters Multiplicative uses a private seasonal profile on an ongoing basis.

For seasonal profiles, a seasonal index is used to bias the standard forecast and is calculated relative to the average demand. It consists of 12 slices (for monthly forecasting) or 52 slices (for weekly forecasting) that indicate the deviation from the average demand. If a slice equals the average slice then the index is 1.0. If a slice is half the average slice, then the index would be 0.5. If the slice is twice the average slice, then the index is 2.0. The total of all indices adds up to 12 (for monthly forecasting) or 52 (for weekly forecasting).

Deseasonalized history is used as an input in the forecast calculation for all of the demand based forecast methods. The total demand that is used to calculate deseasonalized history is defined as:

The forecast that was calculated using deseasonalized history is then multiplied by the seasonal index of the slice to get the final forecast.