Granted Patent B2

US 11,734,712 · App. 14/825,978 · Granted Aug 22, 2023

Inventors: David Shim (Seattle, WA); Elliott Waldron (Seattle, WA); Weilie Yi (Carlsbad, CA); Nick Gerner (Seattle, WA); George Varghese (Kirkland, WA); Andrea Eatherly (New York, NY)

Assignee: FOURSQUARE LABS, INC.

G06Q30/0246

Abstract

Claims (58)

1. A computer-implemented method of analyzing an impact of a campaign on visitation behavior associated with a location, the method comprising:

providing a graphical user interface for displaying campaign data;

generating an alert to indicate that impression data is available for processing using a core pipeline, wherein the core pipeline comprises: a server API, a user profile, and a place service, and wherein the core pipeline is operable to:

receive a web service query comprising report configuration parameters; and

based upon the report configuration parameters, retrieving the impression data;

in response to generation of the alert, accessing, via the core pipeline, impression data for an impression population of impression users, wherein the impression data comprises user identifiers of the impression users exposed to media relating to the campaign;

generating a set of baseline user data based on the location, wherein the baseline user data comprises raw location and device sensor readings used to determine a set of baseline uses who visited the location, and wherein the baseline users have not been exposed to the media relating to the campaign;

generating user identifiers for baseline users in the set of baseline user data;

generating a baseline conversation rate for the baseline users;

hashing the user identifiers of the baseline users to protect a privacy of the baseline population;

hashing the user identifiers of the impression users to protect a privacy of the impression population;

performing a comparison of the hashed baseline user identifiers against the hashed impression user identifiers to identify a first set of hashed user identifiers, the first set of hashed user identifiers including user identifiers that are among both the hashed baseline user identifiers and the hashed impression user identifiers;

identifying a second set of hashed user identifiers, the second set comprising hashed user identifiers that are not among the first set of hashed user identifiers or the hashed impression users;

determining, based on one or more analyses that include a lift analysis of the second set and the first set, a conversion rate of the media relating to the campaign;

upon determining the conversion rate of the media, updating the user interface to present the conversion rate of the media, campaign data, and demographic data included as part of an updated attribution report generated for the campaign.

2. The method of claim 1 , wherein the determining the conversion rate of the media includes determining the conversion rate of the media during a window of time.

3. The method of claim 2 , wherein the window of time is relative to the media consumption by a user.

4. The method of claim 1 , wherein the user identifiers of the baseline users and the user identifiers of the impression users comprise device identifiers.

5. The method of claim 1 , wherein the impression data further comprises a media identifier that identifies attributes of the media relating to the campaign, and a timestamp that indicates when the media relating to the campaign was consumed.

6. The method of claim 1 , wherein the method further comprises:

monitoring a source database;

detecting the impression data within the source database; and

accessing the impression data at the source database in response to the detecting the impression data within the source database.

7. The method of claim 1 , further comprising:

identifying, from the user identifiers of the impression users, a first group of users associated with a demographic feature;

identifying, from the user identifiers of the baseline users, a second group of users associated with the demographic feature; and

calculating an impression index for the demographic feature based on a difference between the user identifiers of the impression users and the user identifiers of the baseline users.

8. A non-transitory computer-readable storage medium whose contents, when executed by a computing device, cause the computing device to perform operations for attributing a conversion event to a campaign associated with a location, the operations comprising:

generating an alert to indicate that impression data is available for processing using a core pipeline, wherein the core pipeline comprises: a server API, a user profile, and a place service, and wherein the core pipeline is operable to:

receive a web service query comprising report configuration parameters; and

based upon the report configuration parameters, retrieving the impression data;

in response to generation of the alert, accessing, via the core pipeline, impression data for an impression population of impression users, wherein the impression data comprises user identifiers of the impression users exposed to media relating to the campaign;

generating a set of baseline user data based on the location, wherein the baseline user data comprises raw location and device sensor readings used to determine a set of baseline uses who visited the location, and wherein the baseline users have not been exposed to the media relating to the campaign;

generating user identifiers for baseline users in the set of baseline user data;

generating a baseline conversation rate for the baseline users;

generating a baseline conversation rate for the baseline users;

hashing the user identifiers of the baseline users to protect a privacy of the baseline population;

hashing the user identifiers of the impression users to protect a privacy of the impression population;

performing a comparison of the hashed baseline user identifiers against the hashed impression user identifiers to identify a first set of hashed user identifiers, the first set of hashed user identifiers including user identifiers that are among both the hashed baseline user identifiers and the hashed impression user identifiers;

identifying a second set of hashed user identifiers, the second set comprising hashed user identifiers that are not among the first set of hashed user identifiers or the hashed impression users;

determining, based on one or more analyses that include a lift analysis of the second set and the first set, a conversion rate of the media relating to the campaign; and

presenting the conversion rate of the media within an updated report, the updated report including a display of an amount of money spent on the campaign, and a count that indicates a number of user identifiers among the first set of user identifiers.

9. An attribution system, comprising:

a memory; and

at least one hardware processor coupled to the memory and comprising instructions that causes the system to perform operations comprising:

generating an alert to indicate that impression data is available for processing using a core pipeline, wherein the core pipeline comprises: a server API, a user profile, and a place service, and wherein the core pipeline is operable to:

receive a web service query comprising report configuration parameters; and

based upon the report configuration parameters, retrieving the impression data;

in response to generation of the alert, accessing, via the core pipeline, impression data for an impression population of impression users, wherein the impression data comprises user identifiers of the impression users exposed to media relating to the campaign;

generating a set of baseline user data based on the location, wherein the baseline user data comprises raw location and device sensor readings used to determine a set of baseline uses who visited the location, and wherein the baseline users have not been exposed to the media relating to the campaign;

generating user identifiers for baseline users in the set of baseline user data; generating a baseline conversation rate for the baseline users;

generating a baseline conversation rate for the baseline users;

hashing the user identifiers of the baseline users to protect a privacy of the baseline population;

hashing the user identifiers of the impression users to protect a privacy of the impression population;

performing a comparison of the hashed baseline user identifiers against the hashed impression user identifiers to identify a first set of hashed user identifiers, the first set of hashed user identifiers including user identifiers that are among both the hashed baseline user identifiers and the hashed impression user identifiers;

identifying a second set of hashed user identifiers, the second set comprising hashed user identifiers that are not among the first set of hashed user identifiers or the hashed impression users;

determining, based on one or more analyses that include a lift analysis of the second set and the first set, a conversion rate of the media relating to the campaign; and

presenting the conversion rate of the media within an updated report, the updated report including a display of an amount of money spent on the campaign, and a count that indicates a number of user identifiers among the first set of user identifiers.

Assignments (8)

Cited By (1)

US 12,418,418