Methods and apparatus to monitor in-store media and consumer traffic related to retail environments

• US 8,818,841 B2
• Filed: 04/25/2008
• Issued: 08/26/2014
• Est. Priority Date: 04/27/2007
• Status: Active Grant

• Current Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Original Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Inventors: Cakora, Matthew C., Brown, Daniel G., Zenor, Michael J., Piotrowski, Frank W., Dupr, William J.
• Primary Examiner(s): Rines, David
• Application Number:
  US12/110,146
• Publication Number:
  US 20080294476A1
• Time in Patent Office: 2,314 Days
• Field of Search: None
• US Class Current: 705/7.37
• 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 30/0203 Market surveys; Market polls
• CPC Class Codes: G06Q 30/0204 Market segmentation
• CPC Class Codes: G06Q 30/0205 Location or geographical consideration

Abstract

Methods and apparatus to monitor in-store media and consumer traffic related to retail environments are disclosed herein. In a disclosed example method to monitor a monitored establishment, a survey is presented to an auditor and a user-provided survey response is received indicative of a condition in a monitored establishment that affects an accuracy of shopper count information provided by the auditor. Instructions are displayed to the auditor to sequentially move to a plurality of predetermined locations in the monitored establishment and collect a shopper count corresponding to each of the predetermined locations. The example method also involves receiving and storing each of the plurality of shopper counts.

Claims

1. A method, comprising:

generating a dependent canonical weight coefficient, an independent canonical weight coefficient, and a regression coefficient based on in-person-based shopper count data collected by a person located in a second establishment, and sensor-based shopper count data collected using an electronic detector in the second establishment,

the dependent canonical weight coefficient to transform shopper count data to generate a shopper traffic variate,

the independent canonical weight coefficient to transform sales data to generate a sales variate, and

the regression coefficient to reduce an amount of error in a best-fit correlation between the shopper traffic variate and the sales variate;

using sales data of a first establishment in which shopper counts are not collected to predict a shopper traffic count based on the dependent canonical weight coefficient, the independent canonical weight coefficient, and the regression coefficient;

receiving information media data indicative of one or more marketing campaigns; and

determining, via a processor, an influential effect of the one or more marketing campaigns on the predicted shopper traffic count in the first establishment.

2. A method as defined in claim 1, wherein the dependent canonical weight coefficient, the independent canonical weight coefficient, and the regression coefficient are further based on an auditor count collected by a second person instructed to move between a plurality of areas of the second establishment and count shoppers in the plurality of areas.

3. A method as defined in claim 1, wherein the in-person-based shopper count data and the sensor-based shopper count data are associated with substantially the same set of shoppers in an area of the second establishment.

4. A method as defined in claim 1, wherein the sales data of the first establishment is representative of sales transactions attributable to individual shoppers.

5. A method as defined in claim 1, further comprising determining opportunities for exposure to information media in the first establishment in which shopper counts are not collected, the opportunities for exposure based on advertisements presented in the first establishment from the one or more marketing campaigns.

6. A method as defined in claim 1, wherein predicting the shopper traffic count comprises predicting the shopper traffic count for a first one of a plurality of zones in the first establishment, the in-person-based shopper count data being collected by the person located in a second zone of the second establishment, and the sensor-based shopper count data being collected using the electronic detector in the second zone of the second establishment.

7. A method as defined in claim 6, wherein the first zone of the first establishment and the second zone of the second establishment correspond to the same product category.

8. An apparatus, comprising:

a traffic count calibrator to generate a prediction model comprising a dependent canonical weight coefficient, an independent canonical weight coefficient, and a regression coefficient based on in-person-based shopper count data and sensor-based shopper count data collected in a first establishment to predict a shopper traffic count in a second establishment in which shopper counts are not collected, the in-person-based shopper count data collected by a person located in the first establishment, and the sensor-based shopper count data collected using an electronic detector in the first establishment,

the dependent canonical weight coefficient to transform shopper count data to generate a shopper traffic variate,

the independent canonical weight coefficient to transform sales data to generate a sales variate, and

the regression coefficient to reduce an amount of error in a best-fit correlation between the shopper traffic variate and the sales variate;

a traffic count generator to predict the shopper traffic count for the second establishment based on the prediction model and sales data of the second establishment;

a database to store information media data indicative of one or more marketing campaigns; and

a processor to determine an influential effect of the one or more marketing campaigns on the predicted shopper traffic count in the first establishment.

9. An apparatus as defined in claim 8, wherein the traffic count calibrator is to generate the prediction model based on an auditor count collected by a second person instructed to move between a plurality of areas of the second establishment and count shoppers in the plurality of areas.

10. An apparatus as defined in claim 8, wherein the in-person-based shopper count data and the sensor-based shopper count data are associated with substantially a same set of shoppers in an area of the second establishment.

11. An apparatus as defined in claim 8, wherein the sales data of the second establishment is representative of sales transactions attributable to individual shoppers.

12. An apparatus as defined in claim 8, wherein the database is to store opportunities for exposure to information media in the first establishment in which shopper counts are not collected, the opportunities for exposure based on advertisements presented in the first establishment from the one or more marketing campaigns.

13. An apparatus as defined in claim 8, wherein the in-person-based shopper count data is collected by the person when the person is located in a first one of a plurality of zones of the first establishment, the sensor-based shopper count data being collected by the electronic detector located in the first zone of the first establishment, and the traffic count generator to predict the shopper traffic count for a second zone of the second establishment.

14. An apparatus as defined in claim 13, wherein the first zone of the first establishment corresponds to a same product category as the second zone of the second establishment.

15. A tangible machine accessible memory comprising instructions stored thereon that, when executed cause a machine to at least:

generate a dependent canonical weight coefficient, an independent canonical weight coefficient, and a regression coefficient based on in-person-based shopper count data collected by a person located in a second establishment, and sensor-based shopper count data collected using an electronic detector in the second establishment,

the dependent canonical weight coefficient to transform shopper count data to generate a shopper traffic variate,

the independent canonical weight coefficient to transform sales data to generate a sales variate, and

the regression coefficient to reduce an amount of error in a best-fit correlation between the shopper traffic variate and the sales variate;

use sales data of a first establishment in which shopper counts are not collected to predict a shopper traffic count based on the dependent canonical weight coefficient, the independent canonical weight coefficient, and the regression coefficient;

receive information media data indicative of one or more marketing campaigns; and

determine an influential effect of the one or more marketing campaigns on the predicted shopper traffic count in the first establishment.

16. A machine accessible memory, as defined in claim 15 having instructions stored thereon that, when executed cause the machine to determine the dependent canonical weight coefficient, the independent canonical weight coefficient, and the regression coefficient based on an auditor count collected by a second person instructed to move between a plurality of areas of the second establishment and count shoppers in the plurality of areas.

17. A machine accessible memory, as defined in claim 15, wherein the in-person-based shopper count data and the sensor-based shopper count data are associated with substantially a same set of shoppers in an area of the second establishment.

18. A machine accessible memory, as defined in claim 15, wherein the sales data of the first establishment is representative of sales transactions attributable to individual shoppers.

19. A machine accessible memory, as defined in claim 15 having instructions stored thereon that, when executed, cause the machine to determine opportunities for exposure to information media in the first establishment in which shopper counts are not collected, the opportunities for exposure based on advertisements presented in the first establishment from the one or more marketing campaigns.

20. A machine accessible memory, as defined in claim 15 having instructions stored thereon that, when executed, cause the machine to predict the shopper traffic count by predicting the shopper traffic count for a first one of a plurality of zones in the first establishment, the in-person-based shopper count data being collected by the person located in a second zone of the second establishment, and the sensor-based shopper count data being collected using the electronic detector in the second zone of the second establishment.

21. A machine accessible memory, as defined in claim 20, wherein the first zone of the first establishment and the second zone of the second establishment correspond to the same product category.