Computer program product and method for estimating internet traffic

• US 8,135,833 B2
• Filed: 06/01/2011
• Issued: 03/13/2012
• Est. Priority Date: 03/07/2002
• Status: Expired due to Term

• Current Assignee: comScore, Inc.
• Original Assignee: Compete, Inc. (comScore, Inc.)
• Inventors: Cancel, David, Moores, Lauren S, Currea, Laura
• Primary Examiner(s): WASEL, MOHAMED A
• Application Number:
  US13/150,370
• Publication Number:
  US 20110296014A1
• Time in Patent Office: 286 Days
• Field of Search: 709/223, 709/224
• US Class Current: 709/224
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

Site metrics are presented in association with search results. The site metrics are derived from site analytics that uses clickstream data collected from a panel of internet users to generate and present internet activity metrics. Data collected from a community of internet users may be augmented by clickstream data store content, third party content, search results, and other sources to form estimates of internet activity, such as traffic, that is structured and analyzed to produce metrics of nearly any internet web site or domain. The data may be further augmented with ratings, such as web site trust ratings, retail deals, and analysis of web site content to form a comprehensive set of data that is mined to formulate various metrics of internet activity about web sites. Metrics of internet activity, a.k.a. site analytics, provides analysis that represents aspects of internet user access to a web site. Such aspects may include activity related to visitors, engagement, growth, trust, deals, and the like.

Claims

1. A method of estimating Internet traffic, the method comprising:

taking a size and demographic composition of a target population;

identifying a group of participants within the target population;

determining demographic information for each member of the group of participants;

receiving clickstream data at a host processing facility from the group of participants that connotes Internet activity of individual members of the group of participants;

scaling the clickstream data for each member of the group of participants to the relative size and demographic composition of the target population and the group of participants by applying a factor related to at least one of the size of the group of participants, a static value and a dynamic value; and

producing, at the host processing facility, an estimate of the target population'"'"'s Internet activity based on the scaled clickstream data; and

refining the estimate of the target population'"'"'s Internet activity by applying a bias adjustment to the estimate, wherein applying the bias adjustment to the estimate comprises applying a weight to a subset of the clickstream data from the group of participants.

2. The method of claim 1, wherein the static values are hardcoded.

3. The method of claim 1, wherein the static values are based upon a heuristic.

4. The method of claim 1, wherein the dynamic values are calculated according to at least one of a formula, function, and algorithm.

5. The method of claim 1, wherein the bias adjustment is at least one of a domain-specific, page-specific, segment-specific, and user-specific adjustment.

6. The method of claim 5, wherein the domain-specific bias is a promotional bias.

7. The method of claim 6, wherein the promotional bias occurs when a source of clickstream data has a higher-than-relative growth in traffic when compared with other sources of clickstream data.

8. The method of claim 5, wherein the domain-specific bias is a structural bias.

9. The method of claim 8, wherein the structural bias occurs when a web site is overrepresented or underrepresented due to the makeup of the sample population, wherein the domain-specific adjustment is a weight calculated using triangulation.

10. The method of claim 5, wherein the domain-specific bias is determined by comparing a selection of the most trafficked domains for both penetration and period-to-period growth across all sources of clickstream data and determining that the sources of clickstream data disagree.

11. The method of claim 5, wherein the domain-specific bias is determined by applying a rules-based process to a matrix of all data from all sources for a selection of domains.

12. The method of claim 1, further comprising, applying an inflation adjustment to the scaling to account for a variation in the Internet behavior of the sample population.

13. The method of claim 12, wherein the variation is due to at least one of attrition within the community of participants, variability of the estimated makeup of the target population, reformulation of the target population, and modification of a benchmark or other basis used to formulate or estimate the target population.

14. The method of claim 1, wherein the Internet activity comprises a physical activity of the individual members of the group of participants, the physical activity selected from the group consisting of clicking, dwelling, and viewing.

15. The method of claim 1, wherein the size and demographic composition of at least one of the target population and the group of participants is updated periodically.

16. The method of claim 1, wherein the demographic composition groups the population based on at least one of gender, age, income, and geography.

17. The method of claim 1, wherein new members are added periodically to the group of participants.

18. The method of claim 1, wherein members are periodically removed from the group of participants, and wherein upon removing members from the group, adjusting the weight of the clickstream data from the remaining members.

19. The method of claim 1, further comprising, adjusting the weight applied to the clickstream data related to the Internet activity of a new member of the group of participants.

20. A memory having computer executable code stored therein, the computer executable code adapted to be run on at least one computing device, the computer executable code realizing a process comprising:

receiving clickstream data at a host processing facility, the data from a group of participants that connotes Internet activity of individual members of the group of participants, wherein the group of participants is identified from within a target population for which a size and demographic composition is taken;

scaling the clickstream data for each member of the group of participants to the relative size and demographic composition of the target population and the group of participants by applying a factor related to at least one of the size of the group of participants, a static value and a dynamic value; and

producing, at the host processing facility, an estimate of the target population'"'"'s Internet activity based on the scaled clickstream data; and

refining the estimate of the population'"'"'s Internet activity by applying a domain-specific bias adjustment to the estimate, wherein applying the domain-specific bias adjustment to the estimate comprises applying a weight to a subset of the data from the group of participants, the subset of the data that connotes a specific domain.