Spatial Data Mining for Retail Sales Forecasting

This paper presents a use case of spatial data mining for aggregate sales forecasting in retail location planning. In particular, the data mining technique Support Vector Regression (SVR) is used to design a regression model to predict probable turnovers for potential outlet-sites of a big European food retailing company. The forecast of potential sites is based on sales data on shop level for existing stores and a broad variety of spatially aggregated geographical, socio-demographical and economical features describing the trading area and competitor characteristics. The model building process was guided by a-priori expert knowledge and by analytic knowledge which was discovered during the data mining process itself. To assess the performance of this SVR-model, it is tested against the traditional state-of-the-art gravitational Huff-model.