Abstract: The present disclosure relates generally to a risk-based fraud identification and risk analysis system. For example, the system may receive application data from a first borrower user, determine a segment associated with the application data, apply application data to one or more machine learning (ML) models, and receive a score based at least in part upon output of the ML model.

Abstract: The present disclosure relates generally to a risk-based fraud identification and risk analysis system. For example, the system may receive application data from a first borrower user, determine a segment associated with the application data, apply application data to one or more machine learning (ML) models, and receive a score based at least in part upon output of the ML model.

Abstract: The present disclosure relates generally to a calculated probability that an income value has been misrepresented in a risk analysis system. For example, the system may apply first data to a first machine learning (ML) model to determine a conservative income prediction associated with the data and apply second data to a second ML model to determine a probability that an overstatement of the income value would result in a change in an approval determination.

Abstract: The present disclosure relates generally to a multi-layer fraud identification and risk analysis system. For example, the system may receive application data from a first borrower user, apply application data to one or more machine learning (ML) models, and receive a first score based at least in part upon output of the ML model that is associated with the first borrower user. The system may aggregate scores associated with multiple borrower users to a cumulative dealer user level. The aggregated first scores associated with the dealer user, as well as other corresponding application data, may be provided as input to a second ML model. Output from the second ML model may be associated with the dealer user as a second score.

Abstract: The present disclosure relates generally to a multi-layer fraud identification and risk analysis system. For example, the system may receive a plurality of first scores associated with borrower users and a dealer user based at least in part upon output of the first ML model. The system may receive a request from a lender user device for a second score, where the dealer user and the lender user device are associated according to a correlative score. The plurality of applications and the correlative score may be used as input to the second ML model that quantifies the risk of the dealer user specifically to the lender user, based on attributes associated with the application data, dealer user, and/or lender user. Output from the second ML model may be provided to the lender user device.

Abstract: The present disclosure relates generally to a risk-based fraud identification and risk analysis system. For example, the system may receive application data from a first borrower user, determine a segment associated with the application data, apply application data to one or more machine learning (ML) models, and receive a score based at least in part upon output of the ML model.

Abstract: The present disclosure relates generally to a risk-based fraud identification and risk analysis system. For example, the system may receive application data from a first borrower user, determine a segment associated with the application data, apply application data to one or more machine learning (ML) models, and receive a score based at least in part upon output of the ML model.

Abstract: The present disclosure relates generally to a risk-based fraud identification and risk analysis system. For example, the system may receive application data from a first borrower user, determine a segment associated with the application data, apply application data to one or more machine learning (ML) models, and receive a score based at least in part upon output of the ML model.

Abstract: The present disclosure relates generally to a multi-layer fraud identification and risk analysis system. For example, the system may receive application data from a first borrower user, apply application data to one or more machine learning (ML) models, and receive a first score based at least in part upon output of the ML model that is associated with the first borrower user. The system may aggregate scores associated with multiple borrower users to a cumulative dealer user level. The aggregated first scores associated with the dealer user, as well as other corresponding application data, may be provided as input to a second ML model. Output from the second ML model may be associated with the dealer user as a second score.

Abstract: The present disclosure relates generally to a multi-layer fraud identification and risk analysis system. For example, the system may receive a plurality of first scores associated with borrower users and a dealer user based at least in part upon output of the first ML model. The system may receive a request from a lender user device for a second score, where the dealer user and the lender user device are associated according to a correlative score. The plurality of applications and the correlative score may be used as input to the second ML model that quantifies the risk of the dealer user specifically to the lender user, based on attributes associated with the application data, dealer user, and/or lender user. Output from the second ML model may be provided to the lender user device.