Dynamic geo-location parameter for determining an impact of online behavior on offline sales

• US 8,429,013 B2
• Filed: 02/05/2009
• Issued: 04/23/2013
• Est. Priority Date: 10/15/2008
• Status: Active Grant

• Current Assignee: Accenture Global Services Limited (Accenture PLC)
• Original Assignee: Accenture Global Services Limited (Accenture PLC)
• Inventors: Symons, Matthew, Fender, Miles, Bose, Piu
• Primary Examiner(s): OBEID, FAHD A
• Application Number:
  US12/366,118
• Publication Number:
  US 20100094682A1
• Time in Patent Office: 1,538 Days
• Field of Search: None
• US Class Current: 705/14.49
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0205 Location or geographical consideration

Abstract

Online behavior of users related to a product is captured. Also, offline sales for the product is also captured. Geo-location parameters are also determined for the captured online and offline data. Using the geo-location parameters and captured data for the product, a smallest geo-location parameter of statistical significance for estimating an impact of the online behavior on offline sales is determined.

Claims

1. A computer system to correlate online behavior with offline sales for a product, the system comprising:

data storage to store online behavior data and offline sales data for the product;

a dynamic regioning module implemented by a processor to;

determine online behavior of users, wherein the online behavior is related to the product,

determine granularities of the geo-location parameter for the on-line behavior of users,

determine a smallest granularity of the granularities of the geo-location parameter,

determine whether the smallest granularity is statistically significant for estimating an impact of the online behavior on offline sales of the product based on the online behavior data and the offline sales data and one or more parameters associated with the online behavior and offline sales,

in response to a determination that the smallest granularity is statistically significant, use the smallest granularity as the smallest geo-location parameter, and

in response to a determination that the smallest granularity is not statistically significant, repeatedly determine whether a next higher granularity of the granularities is statistically significant until a granularity of statistical significance is determined and select the statistically significant granularity as the smallest geo-location parameter; and

a consolidation module, implemented by the processor, to consolidate the stored online behavior data and offline sales data based on the smallest geo-location parameter.

2. The computer system of claim 1, further comprising:

a marketing return on investment (MROI) model, wherein the consolidated data is input into the MROI model to determine the impact of the online behavior on the offline sales of the product for the smallest geo-location parameter.

3. The computer system of claim 2, wherein the dynamic regioning module is to determine whether the smallest granularity is statistically significant from a minimum number of data points for the online behavior data and the offline sales data that are needed to avoid or minimize a probability of failing to detect real effects of the online behavior on the offline sales for the smallest granularity.

4. The computer system of claim 3, wherein one of the granularities is selected as the smallest geo-location parameter of statistical significance based on one or more of amount of online behavior data and offline sales data for each granularity, type of product, type of brand, purchase cycle of the product, and seasonality factors.

5. A method to correlate online behavior with offline sales, the method comprising:

receiving, by a network interface, online behavior data captured from web sites and receiving offline sales data for a product captured from store sales;

storing, by a data storage, the received online behavior data and offline sales data;

determining, by a processor, granularities of a geo-location parameter for on-line behavior of users;

determining a smallest granularity of the granularities of the geo-location parameter;

determining whether the smallest granularity is statistically significant for estimating an impact of the online behavior on offline sales of the product based on the online behavior data and the offline sales data and one or more parameters associated with the online behavior and offline sales;

in response to determining the smallest granularity is statistically significant, using the smallest granularity as a smallest geo-location parameter;

in response to determining the smallest granularity is not statistically significant, repeatedly determine whether a next higher granularity of the granularities is statistically significant until a granularity of statistical significance is determined and select the statistically significant granularity as the smallest geo-location parameter; and

use the smallest geo-location parameter to consolidate data for the online behavior data and data for offline sales.

6. The method of claim 5, further comprising determining whether the smallest granularity is statistically significant from a minimum number of data points for the online behavior data and the offline sales data that are needed to avoid or minimize a probability of failing to detect real effects of the online behavior on the offline sales for the smallest granularity.

7. The method of claim 5, further comprising consolidating the stored online behavior data and offline sales data based on the smallest geo-location parameter.

8. At least one computer readable medium storing computer code that when executed on one or more computer systems is to:

determine online behavior of users, wherein the online behavior is related to a product;

determine granularities of a geo-location parameter for the on-line behavior of users;

determine a smallest granularity of the granularities of the geo-location parameter;

determine whether the smallest granularity is statistically significant for estimating an impact of the online behavior on offline sales of the product based on one or more parameters associated with the online behavior and offline sales;

in response to determining the smallest granularity is statistically significant, use the smallest granularity as a smallest geo-location parameter;

in response to determining the smallest granularity is not statistically significant, repeatedly determine whether a next higher granularity of the granularities is statistically significant until a granularity of statistically significance is determined, and select the statistically significant granularity as the smallest geo-location parameter; and

use the smallest geo-location parameter to consolidate data for the online behavior data and data for offline sales.

9. The at least one computer readable medium of claim 8, wherein the smallest granularity is determined to be statistically significant from a minimum number of data points for the online behavior data and the offline sales data that are needed to avoid or minimize a probability of failing to detect real effects of the online behavior on the offline sales for the smallest granularity.

10. The at least one computer readable medium of claim 8, wherein to determine whether the smallest granularity is statistically significant, the code is to:

identify one or more variables operable to be used to characterize a statistical significance of the geo-location parameters for the online behavior of users; and

use the one or more variables to determine whether the smallest geo-location parameter is statistically significant.

11. The at least one computer readable medium of claim 10, wherein the one or more variables include an amount of online behavior data and offline sales data for each granularity, type of product, type of brand, purchase cycle of the product, and seasonality factors.

12. The at least one computer readable medium of claim 10, wherein the smallest geo-location parameter is determined over time as online and offline product data and one or more of the variables vary over time.

13. The at least one computer readable medium of claim 8, wherein the code is to:

input online behavior of users related to the product and for the smallest geo-location parameter into a marketing return on investment (MROI) model;

input offline sales data of the product for the smallest geo-location parameter into the MROI model; and

estimate the impact of the online behavior on the offline sales of the product for the smallest geo-location parameter.

14. The at least one computer readable medium of claim 13, wherein the code is to:

modify a business practice related to the product in response to the estimated impact.

15. The at least one computer readable medium of claim 13, wherein the code is to:

modify a web site for the product and associated with the smallest geo-location parameter in response to the estimated impact.

16. The at least one computer readable medium of claim 8, wherein the code is to:

perform a reverse Internet Protocol lookup for events captured for the online behavior to determine the geo-location parameters.

17. The at least one computer readable medium of claim 8, wherein the user geo-location parameters for the users comprises a geographic location for each of the users.

18. The at least one computer readable medium of claim 17, wherein the geo-location parameters comprise one or more of GPS coordinates, a group of city blocks, a zip code, and a region encompassing multiple neighboring zip codes.