Tracking Supermarket Shopper Patterns

(Via Knowledge@wharton) Wharton marketing professor Peter S. Fader sees the drawing of shopping cart paths - seemingly random lines represent a new dataset showing the paths taken by individual shoppers in an actual grocery store. The mechanism to collect this unique shopping data is called PathTracker. These RFID tags were placed on the bottom of every grocery cart in a supermarket in the western U.S. The signals are used to chart the position of the grocery cart and record its route through the entire store. This data is translated into the computerized, Etch-a-Sketch-like drawings of shopping cart paths. The data charted for the first time by RFID tags located on consumers' shopping carts, has the potential to change the way retailers in general think about customers and their shopping patterns.
Eric T. Bradlow & Jeffrey S. Larson analyze this RFID-captured grocery store data, focusing exclusively on travel patterns without regard to purchase behavior or merchandising tactics. The results, they conclude, challenge many long-standing perceptions of shopper travel behavior within a supermarket, including ideas related to aisle traffic, special promotional displays, and perimeter shopping patterns.
Using a new "multivariate clustering algorithm," they identified 14 distinct grocery store travel paths during short, medium and long shopping trips. Based on this information, the authors conclude that:
• Grocery shoppers don't weave up and down all aisles - a pattern commonly thought to dominate store travel. Instead, most shoppers "tend only to travel select aisles, and rarely in the systematic up and down patterns most tend to consider the dominant travel pattern."
• Once they enter an aisle, shoppers rarely make it to the other end. Instead, they "travel by short excursions into and out of the aisle rather than traversing its entire length."
• Shoppers prefer a counter-clockwise shopping experience. They tend to shop more quickly as they approach the checkout counters. Shoppers' behavior is driven more by their location in the store than the merchandise in front of them.
• The perimeter of the store - often called the "racetrack" - is actually the shopper's home base, not just the space covered between aisles.
Findings such as these will have important implications for store layouts, product placement, end-cap displays, and relationships between aisles and perimeter spaces - not to mention a better understanding of how consumers shop and how retailers and suppliers can respond to these patterns. "There is a tremendous amount of research available on why people buy what they buy, but until now there was really no research on tracking the actual buying decision," said Fader.
Tagging Grocery Carts - The ability to track 'click-to-click' browsing patterns on the Internet allowed researchers, for the first time, to look at visiting patterns along with purchasing. PathTracker provided the same kind of luxury for ordinary retail stores. Fader likes to call this junction between the traditional retail environment and new kind of tracking technology a "golden spike" - not unlike the joining of the East Coast and West Coast railroad systems in the 19th century. Eventually, continued analyses could show shopping "hot and cold" spots in supermarkets, and predict movements and purchasing patterns that could lead to significant retail adjustments.
Next Logical Step : - A study of the "linkage between travel and purchase behavior - Linking specific travel patterns to individual purchase decisions may lead to an improved understanding of consumer motivations for purchasing certain items, and can shed light on the complementarity and substitutability of goods in ways that a more traditional 'market basket' analysis cannot capture. Further exploration of travel behavior, independent of purchase, also seems another promising route for future research." Amazing are the ways technologies advance and find place in real life business scenarios. The full paper is available here.