Risk assessment in lending
Risk assessment can be performed in many contexts including in lending. A set of metrics can be received and derived from data associated with a party, such as a third-party retailer or dealer, with respect to performance of an activity. A subset of metrics can be identified that exceed a threshold of acceptable performance. Weights can be applied to at least the subset of metrics that captures significance of corresponding metrics. A single weighted score can be computed from aggregation of the weighted subset of metrics, and a third party can be classified based on comparison of the weighted score to a predetermined threshold.
1. A method comprising:
executing, on a processor, instructions that cause a plurality of components to perform operations comprising;
deriving, by a metric component, a set of metrics from data associated with a party with respect to performance of an activity;
identifying, by a trigger component, a subset of metrics of the set of metrics that exceed a first predetermined threshold of acceptable performance;
applying, by a weight assignment component, a weight to the subset of metrics based on significance of a metric;
computing, by a score generation component, a weighted score from aggregation of the weighted subset of metrics;
classifying, by a segmentation component, the party based on comparison of the weighted score to a second predetermined threshold; and
generating, by an interface component, a recommendation of a change in action related to a metric from the subset of metrics that improves the weighted score and classification.
2. The method of claim 1 , wherein the party is a retailer and the activity is origination of a loan for a consumer through a financial institution.
3. The method of claim 2 , wherein the weighted score captures a risk level with respect to compliance with policies or regulations regarding indirect lending.
4. The method of claim 2 , wherein the retailer is an automobile dealer and the financial institution is a bank.
5. The method of claim 2 , wherein the set of metrics pertain to one or more of loan origination, funding, or collection.
6. The method of claim 2 , wherein the significance of the metric is business significance.
7. The method of claim 2 , the operations further comprising:
generating, by the interface component, a graphical scorecard that identifies multiple parties and associated weighted scores.
8. The method of claim 1 , the operations further comprising:
rank ordering, by the segmentation component, a plurality of parties based on the weighted score.
9. The method of claim 1 , wherein the segmentation component implements a machine learning model for automatically classifying the party.
10. A system comprising:
a processor coupled to a memory that includes instructions that, when executed by the processor, control a plurality of components, the components comprising:
a metric component configured to determine a set of metrics from data associated with a third-party retailer originating a loan for a consumer through a financial institution;
a trigger component configured to identify a subset of metrics of the set of metrics that exceed a first predetermined threshold;
a weight assignment component configured to apply a weight to the subset of metrics based on significance of the metric;
a score generation component configured to compute a weighted score from aggregation of weighted metrics of the subset of metrics; and
a segmentation component configured to classify the third-party retailer in terms of adherence to regulatory requirements based on comparison of the weighted score to a second predetermined threshold.
11. The system of claim 10 , wherein the metric component is configured to determine the set of metrics from information pertaining to one or more of loan origination, funding, or collection.
12. The system of claim 10 , wherein the trigger component is further configured to derive the first predetermined threshold through statistical analysis of metrics associated with multiple third-party retailers.
13. The system of claim 10 , wherein the weight assignment component is further configured to apply a weight to the subset of metrics that is business significant.
14. The system of claim 10 , wherein the score generation component is configured to compute the weighted score capturing risk with respect to compliance with one or more indirect lending regulations.
15. The system of claim 10 , further comprising an interface component configured to generate a graphical scorecard that identifies multiple third-party retailers and the classification of the multiple third-party retailers.
16. The system of claim 10 , further comprising an interface component configured to generate a graphical scorecard comprising the weighted score.
17. A system comprising:
a processor coupled to a memory that includes instructions that, when executed by the processor, control a plurality of components, the components comprising:
a metric component configured to determine a set of metrics associated with a dealer originating a loan for a consumer through a bank;
a trigger component configured to identify one or more outliers from the set of metrics based on a threshold;
a weight assignment component configured to assign a weight to the one or more outliers based on business significance;
a score generation component configured to compute an aggregate score from the one or more outliers and assigned weights; and
a segmentation component configured to classify the dealer as high risk or low risk in terms of adherence with regulatory requirements associated with indirect lending based on the score.
18. The system of claim 17 , wherein the metric component is configured to determine the set of metrics from information pertaining to one or more of loan origination, funding, or collection.
19. The system of claim 17 , further comprising an interface component configured to generate a graphical scorecard that identifies multiple third-party retailers ranked based on respective aggregate scores.
20. The system of claim 19 , wherein the interface component is further configured to convey, for display on a display device, the graphical scorecard.