Optimization of demand forecast parameters

A non-transitory computer-readable medium having instructions stored thereon that, when executed by a processor, cause the processor to determine reliable demand forecast parameters for a demand model for one or more items, comprising:

• receiving historical sales data for the items on a per store basis;
• receiving a plurality of seasonality curves for a first item, each of the seasonality curves representing seasonal variations for demand for the first item;
• determining a repeatability of each of the seasonality curves using a correlation of each seasonality curve over year to year demand and retaining a first seasonality curve based on the repeatability;
• determining a smoothness of the first seasonality curve comprising determining a standard deviation of the first seasonality curve;
• determining a sparsity of the first seasonality curve comprising determining if the first seasonality curve comprises a number of data points that exceed a predetermined threshold;
• based on the determined repeatability, smoothness and sparsity, determine that the first seasonality curve is reliable;
• repeating the receiving the plurality of seasonality curves, determining the repeatability, determining the smoothness, and determining the sparsity to determine a plurality of reliable seasonality curves;
• using the demand model and the reliable seasonality curves, determining a demand forecast for the first item, the demand forecast comprising a prediction of further sales data for the first item;
• electronically sending the demand forecast to an inventory management system;
• and
• at the inventory management system, based on the received demand forecast, electronically determining an amount of inventory for the item for a first store of a plurality of stores and causing the amount of inventory to be sent, using a transportation mechanism, to the first store.

A retail item demand forecasting system comprising:

• one or more processors coupled to one or more point of sale systems, the processors receiving historical sales data for retail items on a per store basis;
• the processors further:
• receiving a plurality of seasonality curves for a first item, each of the seasonality curves representing seasonal variations for demand for the first item;
• determining a repeatability of each of the seasonality curves using a correlation of each seasonality curve over year to year demand and retaining a first seasonality curve based on the repeatability;
• determining a smoothness of the first seasonality curve comprising determining a standard deviation of the first seasonality curve;
• determining a sparsity of the first seasonality curve comprising determining if the first seasonality curve comprises a number of data points that exceed a predetermined threshold;
• based on the determined repeatability, smoothness and sparsity, determine that the first seasonality curve is reliable;
• repeating the receiving the plurality of seasonality curves, determining the repeatability, determining the smoothness, and determining the sparsity to determine a plurality of reliable seasonality curves;
• using the demand model and the reliable seasonality curves, determining a demand forecast for the first item, the demand forecast comprising a prediction of further sales data for the first item;
• electronically sending the demand forecast to an inventory management system;
• and
• at the inventory management system, based on the received demand forecast, electronically determining an amount of inventory for the item for a first store of a plurality of stores and causing the amount of inventory to be sent, using a transportation mechanism, to the first store.