System and method for modeling shopping behavior

• US 20060010030A1
• Filed: 07/11/2005
• Published: 01/12/2006
• Est. Priority Date: 07/09/2004
• Status: Active Grant

• Current Assignee: Shopper Scientist LLC
• Original Assignee: Sorensen Associates LLC (TNS Group Holdings Ltd.)
• Inventors: Sorensen, Herb
• Granted Patent: US 8,140,378 B2
• Time in Patent Office: Days
• US Class Current: 705/10
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 30/0204 Market segmentation
• CPC Class Codes: G06Q 30/0205 Location or geographical consideration

Abstract

A system and method are provided for modeling shopper behavior in a store. The system may include an analysis program executable on a computing device, configured to receive product position data and shopper path data gathered from a plurality of stores, each having a different shape represented in a corresponding store map. The analysis program is typically configured to spatially define behavioral domains, product categories, and geographic locations that are common to each of the store maps, and compute statistics based on the product position data and the shopper path data, which statistics are normalized by behavioral domain, product category, and geographic location, across the plurality of stores.

Claims

1. A shopping modeling system, comprising:

an analysis program executable on a computing device, configured to receive product position data and shopper path data gathered from a plurality of stores, each having a different shape represented in a corresponding store map, the analysis program being configured to spatially define behavioral domains, product categories, and geographic locations that are common to each of the store maps, and compute statistics based on the product position data and the shopper path data, which statistics are normalized by behavioral domain, product category, and geographic location, across the plurality of stores.

2. The system of claim 1, wherein the geographic locations are computed by geographic sectors normalized to each of the store maps.

3. The system of claim 1, wherein the geographical locations are computed by a coordinate system normalized to each of the store maps.

4. The system of claim 1, wherein the analysis program is configured to calculate at least one of an expected shopper flow and an expected product purchases for a selected location within the store, based on shopper path data and product position data, and based on a behavioral domain, product category, and geographic location at the selected location.

5. The system of claim 1, wherein the shopper path data is represented via a plurality of linked traffic points extending across each store map.

6. The system of claim 5, wherein the product position data is represented via a plurality of product points extending across each store map.

7. The system of claim 6, wherein one of the behavioral domains is a center-of-store aisle domain.

8. The system of claim 7, wherein the center of store aisles are fractionated by segment according to a normalized aisle depth.

9. The system of claim 8, wherein the center of store aisles are numbered with a normalized aisle index number to indicate relative left to right position in the store.

10. The system of claim 9, wherein the application program is configured to receive a store number, normalized index aisle number, segment number, product point number, and product category as inputs for each product point;

and

wherein the application program is configured to calculate shopper visits, shops, purchases, buy time, and trip decile as outputs for each product point.

11. The system of claim 1, wherein the behavioral domains are selected from the group consisting of bazaar, service, center of store aisle, end caps, service areas, checkout.

12. The system of claim 1, wherein the product categories are selected from the group consisting of frozen foods, salty snacks, dairy, meat, produce, bakery, deli, health and beauty, pet care, and carbonated beverage.

13. A computer-executed shopping analysis method, comprising:

providing a store map for each of a plurality of stores, each having a different physical layout;

identifying a set of behavioral domains;

spatially defining a plurality of the behavioral domains on each of the store maps;

receiving product position data and/or shopper path data for each of the plurality of stores; and

computing a statistical measure of a shopping behavior for at least one of the behavioral domains, based on product position data and/or shopper path data from behavioral domains across the plurality of stores.

14. The method of claim 13, further comprising:

assigning a relationship to at least one of a behavioral domains, product category, and geographic sector, which relates a shopping behavior to a position within the respective behavior domain, product category, or geographic sector.

15. The method of claim 14, wherein the relationship is a shopping behavior-behavioral domain relationship that relates buy time to aisle depth of product position.

16. The method of claim 14, wherein the relationship is a shopping behavior-product category relationship that relates visits, visits to shops, shops, shops to purchases, and/or purchases, to a product category.

17. The method of claim 14, further comprising:

computing at least one of an expected flow of shopper traffic and an expected purchase pattern based upon the assigned relationships and based upon the positions of the products and the behavioral domains.

18. The method of claim 17, further comprising:

spatially defining a plurality of product categories on the store map;

wherein computing at least one of an expected flow of shopper traffic and an expected purchase pattern is further based upon the product categories.

19. The method of claim 17, further comprising:

defining geographic sectors through the store map;

wherein computing at least one of an expected flow of shopper traffic and an expected purchase pattern is further based upon the geographic sectors.

20. A method for analyzing shopping across a plurality of differently shaped stores, comprising:

identifying a set of different types of behavioral domains representing areas of stores in which shoppers exhibit common shopping behaviors;

identifying a set of different types of product categories representing areas of stores in which common products are sold;

inputting a different store map for each of a plurality of stores into an analysis program executed on a computing device;

defining spatial boundaries of a plurality of behavioral domains on each of the store maps;

defining spatial boundaries of a plurality of product categories on each of the store maps;

defining geographic sectors of the store on each of the store maps;

inputting shopper path data and product position data from each of the stores into the analysis program; and

computing statistical measures based on the shopper path data and product position data, normalized across the plurality of stores for at least one of the behavioral domains and/or product categories.