US 12,002,094 B2 · Systems and methods for generating gradient-boosted models with improved fairness

Abstract

Systems and methods for generating tree-based models with improved fairness are disclosed. The disclosed process generates a first tree-based machine learning model, which is preferably trained to predict if a financial loan will be repaid. The process also determines an accuracy of the first tree-based machine learning mode. In addition, the process determines a fairness of the first tree-based machine learning model. The fairness is preferably associated with at least one of gender, race, ethnicity, age, marital status, military status, sexual orientation, and disability status. The process then generates a second different tree-based machine learning model, which is preferably trained based on the accuracy of the first tree-based machine learning model and the fairness of the first tree-based machine learning model. The process then combines the first tree-based machine learning model and the second tree-based machine learning model to produce a gradient-boosted machine learning model.

Claims26

Dependent claims

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.

3 more elements

A modelling system, comprising memory comprising instructions stored thereon and one or more processors coupled to the memory and configured to execute the stored instructions to:

determine an accuracy metric and a fairness metric of a first machine learning model trained to predict loan repayment probability, the fairness metric being associated with a parity between one or more protected or unprotected classes of individuals and the accuracy metric associated with a quality of predictions of the first machine learning model;
deploy a third machine learning model in a production environment, the third machine learning model generated by combining the first machine learning model and a second machine learning model trained based on the accuracy and fairness metrics of the first machine learning model;
apply the third machine learning model to credit application data for a loan to generate a score corresponding to a likelihood that the loan will be repaid;
and
automatically provide an electronic lending decision based on the score and in response to the credit application data.

2 more elements

A non-transitory computer readable medium having stored thereon instructions comprising executable code that, when executed by one or more processors, causes the one or more processors to:

determine an accuracy metric and a fairness metric of a first machine learning model, wherein the fairness metric is associated with one or more protected or unprotected classes of individuals, the accuracy metric is associated with a quality of predictions of the first machine learning model, and the first machine learning model is trained on training data that comprises input training data rows and target labels;
deploy in a production environment a third machine learning model generated by combining the first machine learning model and a second machine learning model, wherein the second machine learning model is trained on the accuracy and fairness metrics of the first machine learning model;
apply the third machine learning model to credit application data for a loan to generate a score corresponding to a likelihood that the loan will be repaid;
and
automatically provide an electronic lending decision based on the score.

2 more elements

Dependencies are inferred from the claim text.

Systems and methods for generating gradient-boosted models with improved fairness

Life of this patent

Systems and methods for generating gradient-boosted models with improved fairness

Life of this patent

Abstract

Claims26