Abstract: Methods and systems for identifying objects based on user-object interactions are disclosed. A system receives a prediction request and inputs parameters associated with the user into a first machine learning model to obtain a first set of object parameters based on a likelihood of interaction with each object based on dynamic features representative of recent user-element interactions. Similarly, the system may input the parameters associated with the user into a second machine learning model to obtain a second set of object parameters based on a likelihood of interaction by the user with each object based on stable features. The system identifies, based on the first and second sets of object parameters, one or more objects for the user and may provide the one or more objects to the user.

Abstract: 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).

Abstract: 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.

Abstract: 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).

Abstract: 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).

Abstract: 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.