System, method and computer program product for demand modeling and prediction in retail categories. The method uses time-series data comprising of unit prices and unit sales for a designated choice set of related products, with the time-series data obtained over a given sequence of sales reporting periods, and over a collection of stores in a market geography. Other relevant data sets from participating retail entities that include additional product attribute data such as market and consumer factors that affect retail demand are further used. A demand model for improved accuracy is achieved by individual sub-modeling method steps of: estimating a model for price movements and price dynamics from the time series data of unit-prices in the aggregated sales data; estimating a model for market share of each product in the retail category using the aggregated sales data and integrated additional product attribute data; and, estimating generating a model for an overall market demand in the retail category from the aggregated sales data.
展开▼
