US 11,720,962 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, Los Angeles, CA (US)
Assigned to ZESTFINANCE, INC., Burbank, CA (US)
Filed by ZestFinance, Inc., Burbank, CA (US)
Filed on Nov. 24, 2021, as Appl. No. 17/535,511.
Claims priority of provisional application 63/117,696, filed on Nov. 24, 2020.
Prior Publication US 2022/0164877 A1, May 26, 2022
Int. Cl. G06Q 20/00 (2012.01); G06Q 40/03 (2023.01); G06N 20/00 (2019.01); G06F 18/243 (2023.01)
CPC G06Q 40/03 (2023.01) [G06F 18/24323 (2023.01); G06N 20/00 (2019.01)] 20 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 and comprising:
training a first tree-based machine learning model to predict loan repayment probability;
determining an accuracy metric and a fairness metric of the first tree-based machine learning model, the fairness being associated with one or more classes of individuals;
training a second different tree-based machine learning model based on the accuracy and the fairness metrics of the first tree-based machine learning model;
deploying a gradient-boosted machine learning model generated by combining the first and second tree-based machine learning models;
applying the gradient-boosted machine learning model to application data for a loan extracted from a received credit application to generate evaluation data comprising at least a score corresponding to a likelihood that the loan will be repaid; and
automatically providing an electronic lending decision in response to the received credit application, wherein the lending decision is based on the score in the evaluation data.