US 12,002,094 B2
Systems and methods for generating gradient-boosted models with improved fairness
Sean Javad Kamkar, Los Angeles, CA (US); Geoffrey Michael Ward, Los Angeles, CA (US); and Jerome Louis Budzik, Burbank, CA (US)
Assigned to ZestFinance, Inc., Burbank, CA (US)
Filed by ZestFinance, Inc., Burbank, CA (US)
Filed on Aug. 7, 2023, as Appl. No. 18/366,413.
Application 18/366,413 is a continuation of application No. 17/535,511, filed on Nov. 24, 2021, granted, now 11,720,962.
Claims priority of provisional application 63/117,696, filed on Nov. 24, 2020.
Prior Publication US 2023/0377037 A1, Nov. 23, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 20/00 (2012.01); G06F 18/243 (2023.01); G06N 20/00 (2019.01); G06Q 40/03 (2023.01)
CPC G06Q 40/03 (2023.01) [G06F 18/24323 (2023.01); G06N 20/00 (2019.01)] 26 Claims
OG exemplary drawing
 
1. A method of automated loan application processing using machine learning credit modeling that maximizes predictive accuracy and outcome parity, the method implemented by a modelling system, the method comprising:
determining an accuracy metric and a fairness metric of a first machine learning model trained to predict loan repayment probability, wherein the accuracy metric represents a quality of predictions of the first machine learning model and the fairness metric represents a parity between one or more protected and unprotected classes of individuals;
training a second machine learning model based on the accuracy and fairness metrics of the first machine learning model;
deploying a third machine learning model in a production environment, wherein the third machine learning model is trained using the first and second machine learning models;
applying the third machine learning model to a credit application for a loan to generate a score corresponding to a likelihood that the loan will be repaid; and
automatically providing an electronic lending decision based on the score and in response to the credit application.