Using basket composition data for intelligent supermarket pricing

How can supermarkets use the vast data they have to design strategies to compete for large-basket shoppers, potentially their most profitable customers? We say, analyze the data to glean basket composition of heterogeneous consumers. Of theoretical and practical interest is the question, will our suggestion improve supermarket profits, and if so, by what pricing strategies? By answering this we can also answer the question, do results of extant research on single-product marketing that using such information intensifies competition and lowers profits, generalize to multiproduct marketing by supermarkets that carry several products, and whose patrons purchase multiple items? We derive equilibrium data-based intelligent pricing strategies that also produce increased supermarket profits. What is more interesting is our result that data analysis is profitable whether or not a competitor undertakes data analysis. If not too costly, implementing data analysis is a dominant strategy. Moreover, with comprehensive data analysis connecting basket information and household data, stores can increase profits further by targeting rewards at individual households, thereby segmenting the market more completely. In contrast to past research findings, we show that for supermarkets, even under competition, use of information on past purchases enables intelligent pricing, better segmentation, and higher profits.