CREATING MICRO-MARKETING PRICING STRATEGIES USING SUPERMARKET SCANNERDATA

Micro-marketing refers to the customization of marketing mix variables to the store-level. This paper shows how prices can be profitably cus tomized at the store-level, rather than adopting a uniform pricing pol icy across all stores. Historically, there has been a trend by retaile rs to consolidate independent stores into large national and regional chains. This move toward consolidation has been driven by the economie s of scale associated with these larger operations. However, some of t hese large chains have lost the adaptability of independent neighborho od stores. Micro-marketing represents an interest on the part of manag ers to combine the advantages of these large operations with the flexi bility of independent neighborhood stores. A basis for these customize d pricing strategies is the result of differences in interbrand compet ition across stores. These changes in interbrand competition are measu red using weekly store-level scanner data at the product level. Obviou sly, this presents a huge estimation problem, since we wish to measure substitution between each product at a store-level. For a chain with 100 stores and 10 products in a category we would need to estimate ove r 100,000 parameters. To reliably estimate these individual store diff erences we phrase our problem in a hierarchical Bayesian framework. Es sentially, each store-level parameter can be thought of as a combinati on of chain-level and random store-specific effects. The improvement i n estimating this model comes from exploiting the common chain-level c omponent. In addition, we relate these store-specific changes to demog raphic and competitive characteristics of the store's trading area, wh ich helps explain why these differences are present. These estimated d ifferences in price response are in turn used to set store-level price s. To simplify and focus the problem we limit our attention to everyda y price changes (i.e., the prices of products that are not advertised) . There are many marketing variables that can be adjusted at a store-l evel (e.g., promotions and product assortments); the reason we concent rate upon everyday pricing is driven by its importance in the marketin g mix, that most profits are earned on products sold at their everyday price, and the amenability of everyday prices to store-level customiz ations. A limitation of this approach is that it yields only a partial solution to the retailer's global optimization problem. A challenge f or the retailer in implementing micro-marketing pricing strategies is to retain a consistent image while altering prices that adapt to neigh borhood differences in demand. Our approach is to search for price cha nges that leave image unchanged. We argue that a sufficient condition for holding the input to store image constant from everyday pricing is to hold average price and revenues at their current levels. We implem ent this condition by introducing constraints into the profit maximiza tion problem. Future research into store choice may yield more efficie nt conditions. A benefit of holding the retailer's image constant is t hat it does not require costly new information about competitors and p romotional activity. Instead, retailers are able to derive these store -level customizations based largely upon scanner data. This is very ad vantageous since this information is already being collected and is re adily available. Our results indicate that micro-marketing pricing str ategies would be profitable and could increase gross profit margins by 4 percent to 10 percent. When these gross profit gains are considered after administrative and operating costs are taken into account, they could increase operating profit margins by 33 percent to 83 percent. These gains come from encouraging consumers through everyday price cha nges to switch to more profitable bundles of products, and not through overall price changes at the chain-level. These results show that the information contained in the retailer's store-level scanner data is a n under-utilized resource. By exploiting this information using newer and more powerful computational techniques managers can better appreci ate its value. The implication is that profits could be increased and gains can be made by using this information as the basis for micro-mar keting.