US 11,983,089 B2
Contribution incrementality machine learning models
Xinlong Bao, Los Altos, CA (US); Ali Nasiri Amini, Redwood City, CA (US); Jing Wang, Mountain View, CA (US); Mert Dikmen, Belmont, CA (US); Amy Richardson, Santa Cruz, CA (US); Dinah Shender, Sunnyvale, CA (US); Junji Takagi, Sunnyvale, CA (US); Sen Li, Mountain View, CA (US); Ruoyi Jiang, Sunnyvale, CA (US); Yang Jiao, San Mateo, CA (US); Yang Zhang, Sunnyvale, CA (US); and Zhuo Zhang, Santa Clara, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Appl. No. 17/278,395
Filed by Google LLC, Mountain View, CA (US)
PCT Filed Dec. 5, 2019, PCT No. PCT/US2019/064752
§ 371(c)(1), (2) Date Mar. 22, 2021,
PCT Pub. No. WO2021/112862, PCT Pub. Date Jun. 10, 2021.
Prior Publication US 2021/0326233 A1, Oct. 21, 2021
Int. Cl. G06Q 30/02 (2023.01); G06F 11/34 (2006.01); G06N 20/00 (2019.01)
CPC G06F 11/3433 (2013.01) [G06F 11/3428 (2013.01); G06N 20/00 (2019.01)] 21 Claims
OG exemplary drawing
 
1. A method comprising:
creating, by one or more computing devices, a model that represents relationships between user attributes, content exposures, and performance levels for a specified target action;
obtaining organic exposure data specifying one or more organic exposures experienced by a particular user over a specified time period prior to performance of a specified target action by the particular user, wherein the organic exposures are neither exposures to a specified type of digital component nor performance of the specified target action;
obtaining third party exposure data specifying third party exposures of the specified type of digital component to the particular user over the specified time period, wherein the third party exposure data includes, for each of the third party exposures, an exposure time specifying when the third party exposure occurred;
determining, using the model, an incremental performance level attributable to each of the third party exposures at an action time when the specified target action was performed by the particular user;
modifying, by the one or more computing devices, transmission criteria for at least some digital components to which the particular user was exposed based on the incremental performance level that is attributed to the third party exposures of the at least some of the digital components.