Abstract: This disclosure describes techniques for determining whether to approve or deny a borrower's lending-product request by selectively using a heuristic and statistical model. More specifically, a borrower may submit a lending-product request to a Statistical Risk Management (SRM) system, and in doing so the SRM system may analyze relationship attributes of the borrower to determine a likelihood of borrower repaying a loan over a predetermined time period, and avoid being charged off. In some examples, the SRM system may execute a plurality of statistical models to determine a charge-off probability score. Each statistical model may be based on a set, or subset of historical lending-product data. A subset of historical lending-product data may be based on a selection bias of shared characteristics within a set of historical lending-product data. The selection bias may be based on characteristics of a lending-product request or relationship attributes of a borrower.

Abstract: This disclosure describes techniques for determining whether to approve or deny a borrower's lending-product request by selectively using a heuristic and statistical model. More specifically, a borrower may submit a lending-product request to a Heuristic-Statistical Risk Management (HS-RM) system, and in doing so the HS-RM system may analyze relationship attributes of the borrower to determine a likelihood of borrower repaying a loan over a predetermined time period, and avoid being charged off. In some examples, the HS-RM system may execute a plurality of statistical models to determine a charge-off probability score. Each statistical model may be based on a set, or subset of historical lending-product data. A subset of historical lending-product data may be based on a selection bias of shared characteristics within a set of historical lending-product data. The selection bias may be based on characteristics of a lending-product request or relationship attributes of a borrower.

Abstract: This disclosure describes techniques for determining whether to approve or deny a borrower's lending-product request by selectively using a heuristic and statistical model. More specifically, a borrower may submit a lending-product request to a Heuristic-Statistical Risk Management (HS-RM) system, and in doing so the HS-RM system may analyze relationship attributes of the borrower to determine a likelihood of borrower repaying a loan over a predetermined time period, and avoid being charged off. In some examples, the HS-RM system may execute a plurality of statistical models to determine a charge-off probability score. Each statistical model may be based on a set, or subset of historical lending-product data. A subset of historical lending-product data may be based on a selection bias of shared characteristics within a set of historical lending-product data. The selection bias may be based on characteristics of a lending-product request or relationship attributes of a borrower.

Abstract: This disclosure describes techniques for determining whether to approve or deny a borrower's lending-product request by selectively using a heuristic and statistical model. More specifically, a borrower may submit a lending-product request to a Statistical Risk Management (SRM) system, and in doing so the SRM system may analyze relationship attributes of the borrower to determine a likelihood of borrower repaying a loan over a predetermined time period, and avoid being charged off. In some examples, the SRM system may execute a plurality of statistical models to determine a charge-off probability score. Each statistical model may be based on a set, or subset of historical lending-product data. A subset of historical lending-product data may be based on a selection bias of shared characteristics within a set of historical lending-product data. The selection bias may be based on characteristics of a lending-product request or relationship attributes of a borrower.

Abstract: A statistical model enables a lender financial institution to leverage multiple relationship attributes of a borrower to predict whether the borrower is capable of timely paying back a loan. The statistical model is generated to provide a multitude of relationship attribute coefficients based on historical borrower data of a multiple borrowers from an alternative loan approval process. The multitude of relationship attribute coefficients are applied to corresponding relationship attribute values of a borrower that is seeking a loan from a financial institution to generate an intermediate borrower score for the borrower. A probability of the borrower not being charged off on a loan after a predetermine time period is then calculated based on the intermediate borrower score. Accordingly, the loan may be determined to be approved or denied based on a comparison of the probability to an approval cutoff threshold.