Predicting shopper traffic at a retail store

• US 7,996,256 B1
• Filed: 09/04/2007
• Issued: 08/09/2011
• Est. Priority Date: 09/08/2006
• Status: Active Grant

• Current Assignee: The Procter & Gamble Company
• Original Assignee: The Procter & Gamble Company
• Inventors: Young, Kathryn Byrd, Anand, Jayaraman, Howell, Dina R., Choudhary, Ranjit Kumar
• Primary Examiner(s): DIXON, THOMAS A
• Application Number:
  US11/899,150
• Time in Patent Office: 1,435 Days
• Field of Search: 705/10
• US Class Current: 705/7.31
• 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 30/0241 Advertisements
• CPC Class Codes: G06V 20/53 Recognition of crowd images, e.g. recognition of crowd congestion
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats

Abstract

Mathematical models for predicting shopper traffic at a shopper region useful for developing inter alia a metric for measuring impressions to in-store advertising.

Claims

1. A method for developing an in-store shopper traffic prediction model, comprising the steps:

(a) obtaining actual shopper traffic data at a first shopper region at a first retail store, wherein the first shopper region comprises at least a first product category;

(b) obtaining actual market data from the first store, wherein the market data comprises category purchase data from the first product category;

(c) inputting the shopper traffic data and the market data in an analysis program executable on a computer;

(d) executing the analysis program to develop a mathematical model capable of predicting shopper traffic at the first shopper region of a target retail store.

2. The method of claim 1, wherein actual shopper traffic data at a first shopper region is further obtained at a plurality of retail stores,

wherein the first shopper region of the plurality of retail stores comprises the same first product category;

wherein the plurality of retail stores comprises at ten stores.

3. The method of claim 2, wherein said actual shopper traffic data and said actual market data is obtained during the same period of time;

and

wherein the market data further comprises at least one of the following;

store purchase data, store data, temporal data, demographic data, or combinations thereof.

4. The method of claim 2, wherein market data further comprises the following:

store purchase data, store data, temporal data, and demographic data; and

wherein the first category purchase data further comprises;

category items, category baskets, category dollars, and category percentage of store dollars;

wherein obtaining actual shopper traffic is measured electronically using a fixed sensor.

5. The method of claim 1, wherein the mathematical model is developed from:

(a) actual shopper traffic data at a first shopper region from a plurality of retail stores,

wherein the first shopper region comprises at least a first product category;

(b) actual market data from said plurality of retail stores,

wherein the market data comprises category purchase data from the first product category.

6. The method of claim 5, wherein the plurality of stores comprises at least thirty stores;

and wherein the retail stores comprise at least three different retail store types, and

wherein the retail store types are chosen from food, super, center, mass merchandiser, club, and drug.

7. The method of claim 6, further comprising the step of normalizing the mathematical model for the period of time from which the actual market data from the target store is obtained;

and the first product category, and wherein the plurality of stores comprises at least thirty stores.