Total structural risk model
AssigneeAmerican Express Travel Related Services Company, Inc.
InventorsTirthankar Choudhuri, Anjali Dewan, Amber Gupta, Kathleen Haggerty, Di Xu, Chao Yuan
Life of this patent
Estimating the term…
Abstract
The present invention generally relates to financial data processing, and in particular it relates to credit scoring, consumer profiling, consumer behavior analysis and modeling. More specifically, it relates to risk modeling using the inputs of credit bureau data, size of wallet data, and, optionally, internal data.
Claims20
A method for determining a comprehensive consumer default risk value for a consumer, wherein said consumer default risk value is derived by a risk analysis computer comprising a processor and a non-transitory memory, said method comprising:
- modeling, by said risk analysis computer, consumer spending patterns of said consumer using credit data associated with said consumer to obtain an estimated spend capacity of said consumer;
- and
- calculating, by said risk analysis computer, said comprehensive consumer default risk value for said consumer based upon consumer transactional data comprising at least one of transaction amount, transaction time, transaction vendor/merchant, and transaction vendor/merchant location, and said estimated spend capacity, wherein said comprehensive consumer default risk value represents a risk associated with said consumer defaulting on an existing debt obligation,
- wherein said calculating comprises:
- assigning, by said risk analysis computer, said consumer to a consumer population segment based upon primary residence value;
- and
- selecting, by said risk analysis computer, an appropriate risk factor relationship based upon said consumer credit data and said internal data.
A system for developing a credit score for an individual consumer, the system comprising:
- a non-transitory memory communicating with a risk analysis processor;
- said non-transitory memory having instructions stored thereon that, in response to execution by said processor, cause said processor to perform operations comprising:
- modeling, by said processor, consumer spending patterns of said consumer using credit data associated with said consumer to obtain an estimated spend capacity of said consumer;
- and
- calculating, by said processor, said comprehensive consumer default risk value for said consumer based upon consumer transactional data comprising at least one of transaction amount, transaction time, transaction vendor/merchant, and transaction vendor/merchant location, and said estimated spend capacity, wherein said comprehensive consumer default risk value represents a risk associated with said consumer defaulting on an existing debt obligation,
- wherein said calculating comprises:
- assigning, by said processor, said consumer to a consumer population segment based upon primary residence value;
- and
- selecting, by said processor, an appropriate risk factor relationship based upon said consumer credit data and said internal data.
An article of manufacture including a non-transitory computer readable medium having instructions stored thereon that, in response to execution by a risk analysis computing device, cause said computing device to perform operations comprising:
- modeling, by said computing device, consumer spending patterns of said consumer using credit data associated with said consumer to obtain an estimated spend capacity of said consumer;
- and
- calculating, by said computing device, said comprehensive consumer default risk value for said consumer based consumer transactional data comprising at least one of transaction amount, transaction time, transaction vendor/merchant, and transaction vendor/merchant location, and said estimated spend capacity, wherein said comprehensive consumer default risk value represents a risk associated with said consumer defaulting on an existing debt obligation,
- wherein said calculating comprises:
- assigning, by said computing device, said consumer to a consumer population segment based upon primary residence value;
- and
- selecting, by said computing device, an appropriate risk factor relationship based upon said consumer credit data and said internal data.
Dependencies are inferred from the claim text.