US 11,810,147 B2
Automated attribution modeling and measurement
Jon Hoffman, New York, NY (US); Adam Poswolsky, Great Neck, NY (US); and Robert Stewart, Brooklyn, NY (US)
Assigned to Foursquare Labs, Inc., New York, NY (US)
Filed by Foursquare Labs, Inc., New York, NY (US)
Filed on Oct. 19, 2017, as Appl. No. 15/788,547.
Prior Publication US 2019/0122251 A1, Apr. 25, 2019
Int. Cl. G06Q 30/0242 (2023.01)
CPC G06Q 30/0242 (2013.01) 20 Claims
OG exemplary drawing
 
1. A system comprising:
at least one processor; and
memory coupled to the at least one processor, the memory comprising computer executable instructions that, when executed by the at least one processor, performs a method comprising:
receiving data from at least one electronic device in an exposed group;
processing data from the at least one electronic device;
creating at least one control group using the data based at least upon a commonality threshold for one or more features, wherein the commonality threshold is determined in accordance with a machine-learning algorithm that receives both non-exposed user profile information and exposed user-profile information as input, wherein the machine learning algorithm is trained using a historical dataset comprising information associated with a preexisting profile database of both exposed and non-exposed individuals from prior campaigns, their associated electronic device data, and a dataset comprising location information from a location-intelligent database;
matching at least one profile from the at least one control group with at least one profile from the exposed group;
automatically monitoring, for a predetermined period of time following the matching, electronic device data associated with:
a first device of the matched at least one profile from the control group; and
a second device of the matched at least one profile from the exposed group, wherein the profiles associated with the first device and the second device have been matched with each other;
comparing the electronic device data for the first device and the second device; and
generating at least one result for at least one of the exposed group and at least one of the control group based on the comparison.