Capital One Services, LLC

John Lujano

Ruoyu Shao

Sang Jin Park

Kurt Wolf

Abhishek Kumar Shrivastava

Heng Gu

Tong Niu

Jacky Kwok

Christopher Cowden

Methods and systems are described herein for a mechanism for detecting model bias using a test model to compare predictions for specific categories of data. Thus, the system may detect category-specific model bias and/or present alternative predictions, for example, via overfitted and alternative machine learning models. Another mechanism for detecting model bias is to use residual data from predictions obtained from a machine learning model as the machine learning model processes different datasets (e.g., a training dataset and a compare dataset).

Detecting category-specific bias using overfitted machine learning models

Disclosed are systems and methods for consolidating credit profiles for co-applicants of a joint loan application. For example, a method may include: obtaining a first model score associated with the first applicant; receiving an address of the first applicant; obtaining a second model score associated with the second applicant; receiving an address of the second applicant; determining that the address of the first applicant and the address of the second applicant are the same; aggregating the first model score and the second model score to generate a joint model score for the first and second applicants based on the determination that the address of the first applicant and the address of the second applicant are the same; and generating the joint application for the first and second applicants at least based on the joint model score.

Methods and systems for consolidating profiles for joint application determination

Growing community of inventors

Dallas, TX, United States of America

John Lujano