US 12,299,748 B2
Method of controlling for undesired factors in machine learning models
Jeffrey S. Myers, Normal, IL (US); Kenneth J. Sanchez, San Francisco, CA (US); and Michael L. Bernico, Bloomington, IL (US)
Assigned to State Farm Mutual Automobile Insurance Company, Bloomington, IL (US)
Filed by STATE FARM MUTUAL AUTOMOBILE INSURANCE COMPANY, Bloomington, IL (US)
Filed on Apr. 13, 2023, as Appl. No. 18/134,373.
Application 18/134,373 is a continuation of application No. 17/591,633, filed on Feb. 3, 2022, granted, now 11,676,217.
Application 17/591,633 is a continuation of application No. 16/720,665, filed on Dec. 19, 2019, granted, now 11,315,191, issued on Apr. 26, 2022.
Application 16/720,665 is a continuation of application No. 16/352,038, filed on Mar. 13, 2019, granted, now 10,769,729, issued on Sep. 8, 2020.
Application 16/352,038 is a continuation of application No. 15/383,659, filed on Dec. 19, 2016, granted, now 10,282,789, issued on May 7, 2019.
Claims priority of provisional application 62/273,624, filed on Dec. 31, 2015.
Claims priority of provisional application 62/272,184, filed on Dec. 29, 2015.
Prior Publication US 2023/0252578 A1, Aug. 10, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 40/08 (2012.01); G06N 3/04 (2023.01); G06N 3/08 (2023.01); G06N 20/00 (2019.01); G06V 10/82 (2022.01); G06V 30/19 (2022.01); G06V 40/16 (2022.01); H04N 7/18 (2006.01); G06Q 30/0207 (2023.01)
CPC G06Q 40/08 (2013.01) [G06N 3/04 (2013.01); G06N 3/08 (2013.01); G06N 20/00 (2019.01); G06V 10/82 (2022.01); G06V 30/19173 (2022.01); G06V 40/169 (2022.01); H04N 7/185 (2013.01); G06Q 30/0207 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for evaluating an insurance applicant as part of an underwriting process using an artificial neural network and one or more processors, the method comprising:
receiving, from or on behalf of the insurance applicant, by the one or more processors, application information including one or more of a still image, a video, or a voice recording of the insurance applicant;
analyzing the application information with the artificial neural network and by the one or more processors to probabilistically determine personal and/or health-related characteristics of the insurance applicant, wherein the artificial neural network is trained to probabilistically determine personal and/or health related characteristics of an individual based upon a training data set including at least images or audio recordings of other individuals having known health related characteristics including one or more pre-identified factors;
further analyzing the application information with the artificial neural network and by the one or more processors to exclude the one or more pre-identified factors to control for an undesired prejudice or discrimination caused by the one or more pre-identified factors; and
outputting with the artificial neural network and by the one or more processors an appropriate insurance premium for the insurance applicant based upon the probabilistically determined personal and/or health-related characteristics of the insurance applicant excluding the one or more pre-identified factors.