# US 8,751,378 B2 · Strategic loan default scoring > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 8,751,378 B2 - Document ID: US8751378B2 - Status: Granted - Kind: B2 - Application number: 13/399,823 - Filed: 2012-02-17 - Published: 2013-08-22 - Granted: 2014-06-10 - Earliest claimed: 2012-02-17 - Assignees: Fair Isaac Corporation - Applicants: Ethan Dornhelm; Lu Gao; Joanne Gaskin; Yan Wei; Tracy Backes; Andrew Leverentz - Inventors: Ethan Dornhelm; Lu Gao; Joanne Gaskin; Yan Wei; Tracy Backes; Andrew Leverentz - Web page: https://patentgrep.com/patent/US8751378B2 ## CPC - G06Q 40/00: Finance; Insurance; Tax strategies; Processing of corporate or income taxes - G06Q 40/02: Banking, e.g. interest calculation or account maintenance (credit or loans G06Q40/03) - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR ## Abstract A strategic default score is determined for an entity that characterizes a likelihood of the entity voluntarily electing to default on a loan. Data characterizing credit data and valuation data of an asset owned by the entity is received. Using the received data, the strategic default score is generated which characterizes a likelihood of the entity to voluntarily elect to default on the loan when the entity is capable of paying-off the loan. Provision (e.g., display, transmission, storage, etc.) of the strategic default score is then initiated. Related apparatus, systems, techniques and articles are also described. ## Claims ### Claim 1 A method for implementation by one or more data processors forming part of at least one computing system, the method comprising: receiving, by at least one data processor, data characterizing credit data of an entity and valuation data of an asset owned by the entity, the asset being secured by a loan of one or more loans; generating, by at least one data processor using the received data, a strategic default score for the entity, the strategic default score indicating that the entity will to voluntarily elect to default on the loan while the entity is capable of paying off the loan and/or while the entity continues to pay other loans, the generating comprising: determining, by at least one data processor using the received data, a ratio of a value of the loan to a current value of the asset, the value of the loan being obtained from the credit data, the value of the asset being obtained from valuation data; determining, by at least one data processor and based on the determined ratio, a segment of a plurality of segments that is associated with the entity; selecting, by at least one data processor, a first predictive model among a plurality of predictive models based on the determined segment; and determining, by at least one data processor and using the selected first predictive model, the strategic default score of the entity, each segment of the plurality of segments being associated with one or more corresponding predictive models that are trained using historical credit data for a plurality of individuals and with historical valuation data for a plurality individuals; and initiating, by at least one data processor, a provision of the strategic default score. ### Claim 2 (depends on 1) The method of claim 1, wherein the first predictive model is optimized using at least one divergence-based optimization algorithm. ### Claim 3 (depends on 2) The method of claim 2, wherein the optimized predictive model is scaled so that the generated strategic default score is within a predetermined range. ### Claim 4 (depends on 1) The method of claim 1, wherein the historical valuation data for each asset comprises a value of the asset and a forecast of expected change in the value over a predetermined period of time. ### Claim 5 (depends on 1) The method of claim 1, wherein the provision of the strategic default score comprises at least one of display, transmission, and storing of the strategic default score. ### Claim 6 A non-transitory computer program product storing instructions which, when implemented by one or more data processors forming part of at least one computing system, result in operations comprising: receiving, by at least one data processor, data characterizing credit data of an entity and valuation data of an asset owned by the entity, the asset being secured by a loan of one or more loans; generating, by at least one data processor using the received data, a strategic default score for the entity, the strategic default score indicating that the entity will voluntarily elect to default on the loan while the entity is capable of paying off the loan and/or while the entity continues to pay other loans, the generating comprising: determining, using the received data, a ratio of a value of the loan to a current value of the asset, the value of the loan being obtained from the credit data, the value of the asset being obtained from valuation data; determining, based on the determined ratio, a segment of a plurality of segments that is associated with the entity; selecting a first predictive model among a plurality of predictive models based on the determined segment; and determining, using the selected first predictive model, the strategic default score of the entity, each segment of the plurality of segments being associated with one or more corresponding predictive models that are trained using historical credit data for a plurality of individuals and with historical valuation data for a plurality of assets corresponding to the plurality of individuals; and initiating provision of the strategic default score. ### Claim 7 (depends on 6) The computer program product of claim 6, wherein the first predictive model is optimized using at least one divergence-based optimization algorithm. ### Claim 8 (depends on 7) The computer program product of claim 7, wherein the optimized predictive model is scaled so that the generated strategic default score is within a predetermined range. ### Claim 9 (depends on 6) The computer program product of claim 6, wherein the historical valuation data for each asset comprises a value of the asset and a forecast of expected change in the value over a predetermined period of time. ### Claim 10 (depends on 6) The computer program product of claim 6, wherein the provision of the strategic default score comprises at least one of display, transmission, and storing of the strategic default score. ### Claim 11 A system comprising: at least one data processor; and memory storing instructions which, when implemented by the at least one data processor, result in operations comprising: receiving, by at least one data processor, data characterizing credit data of an entity and valuation data of an asset owned by the entity, the asset being secured by a loan of one or more loans; generating, by at least one data processor using the received data, a strategic default score for the entity, the strategic default score indicating that the entity will voluntarily elect to default on the loan while the entity is capable of paying off the loan and/or while the entity continues to pay other loans, the generating comprising: determining, by at least one data processor using the received data, a ratio of a value of the loan to a current value of the asset, the value of the loan being obtained from the credit data, the value of the asset being obtained from valuation data; determining, by at least one data processor and based on the determined ratio, a segment of a plurality of segments that is associated with the entity; selecting a first predictive model among a plurality of predictive models based on the determined segment; and determining, by at least one data processor and using the selected first predictive model, the strategic default score of the entity, each segment of the plurality of segments being associated with one or more corresponding predictive models that are trained using historical credit data for a plurality of individuals and with historical valuation data for a plurality of assets corresponding to the plurality of individuals; and initiating, by at least one data processor, a provision of the strategic default score. ### Claim 12 (depends on 11) The system of claim 11, wherein the first predictive model is optimized using at least one divergence-based optimization algorithm. ### Claim 13 (depends on 12) The system of claim 12, wherein the optimized predictive model is scaled so that the generated strategic default score is within a predetermined range. ### Claim 14 (depends on 11) The system of claim 11, wherein the historical valuation data for each asset comprises a value of the asset and a forecast of expected change in the value over a predetermined period of time. ### Claim 15 (depends on 11) The system of claim 11, wherein the provision of the strategic default score comprises at least one of display, transmission, and storing of the strategic default score.