Retail sales forecast system with promotional cross-item effects prediction

A method of predicting promotional cross item (PCI) effects for retail items for a store, the method comprising:

• receiving historical sales data for the store;
• storing the historical sales data in a panel data format;
• aggregating the stored sales data as a first level of aggregation, wherein the first level of aggregation is aggregated to the store, a product and a time period;
• aggregating the first level of aggregation aggregated data as a second level of aggregation, wherein the second level of aggregation is based on a promotional cross effect attribute (PCEA) and is aggregated to the store, the time period and a PCEA level;
• deriving PCI effect predictor variables from the second level of aggregation;
• for each PCEA within a retail item family, forming a regression model;
• and
• generating estimated model parameters for one or more PCI effects for each PCEA from the regression models.

A promotional cross item (PCI) effects estimating system that receives historical sales data for the store, the system comprising:

• a storage module that stores the historical sales data in a panel data format;
• an aggregator module that aggregates the stored sales data as a first level of aggregation, wherein the first level of aggregation is aggregated to the store, a product and a time period, and aggregates the first level of aggregation aggregated data as a second level of aggregation, wherein the second level of aggregation is based on a promotional cross effect attribute (PCEA) and is aggregated to the store, the time period and a PCEA level;
• and
• a regression model module that derives PCI effect estimation variables from the second level of aggregation, for each PCEA within a retail item family, forms a regression model, and generates estimated model parameters for one or more PCI effects for each PCEA from the regression models.