Systems and methods for enrichment of data relating to consumer credit collateralized debt and real property and utilization of same to maximize risk prediction
View Patent ↗Systems and methods for enrichment of data associated with risk prediction. Data may be enriched by incorporating one or more aspects of consumer credit, collateralized debt, mortgage, real property, and loan data for use in systems, products, and methods relying on risk prediction models to maximize the effectiveness of the risk prediction. A time-series of consumer credit data may be provided to provide historical context to data. In a particular application, enriched data is leveraged to predict occurrence of an event relating to underlying assets of a structured security, such as a mortgage-backed security. Other systems and methods are disclosed.
1. A computer system for matching underlying assets of a security to consumer credit data in connection with risk prediction associated with valuation and pricing of the security, the system comprising:
a computer processor in selective communication with a requesting computer to receive an initial set of data associated with the security, the initial set of data comprising records of the underlying assets without sufficient consumer identification data for each consumer associated with each of the underlying assets;
a computer readable medium accessible by the processor;
a database in communication with the processor, the database containing a plurality of credit data files stored thereon, each of the plurality of credit data files associated with a respective consumer; and
software stored on the computer readable medium for executing the steps of:
identifying data in data fields of each of the records from the initial set of data that match data in data fields associated with the plurality of credit data files associated with the respective consumers, wherein at least one data field associated with the records from the initial set of data is matched to a differently named data field associated with the plurality of credit data files;
for each of the matched data fields, assigning a weighted point score corresponding to a quality of the match;
for each of the records from the initial set of data, determining an identity of a consumer associated with the plurality of credit data files that corresponds to a highest point score of the assigned point scores; and
assigning the identity of the identified consumer to the respective record from the initial set of data;
providing a prediction of an occurrence of an event relating to the underlying assets of the security based on the identity of the identified consumer and a time series credit score associated with the identified consumer's credit history over a predetermined period of time and at a predetermined time interval to permit an updated valuation and pricing of the security.
2. The system of claim 1 , wherein the step of providing a prediction of an occurrence of an event comprises determining a vector of probability of the occurrence of the event over the predetermined period of time.
3. The system of claim 2 , wherein the software stored on the computer readable medium executes the additional step of returning the vector of probabilities of the occurrence of the event to the requesting computer.
4. The system of claim 1 , wherein if more than one consumer is identified with the same highest point score, the consumer with a most recent account activity in the respective credit data file is identified and assigned to the respective record.
5. The system of claim 1 , wherein the data fields comprise a zip code for both the initial set of data and the plurality of credit data files, an origination amount for the initial set of data and a high credit amount for the plurality of credit data files, and an origination date for the initial set of data and an account open date for the plurality of credit data files.
6. The system of claim 1 , wherein identifying the data in data fields comprises matching the data associated with a loan servicer name, an account number, and a primary zip code of each of the records from the initial set of data to corresponding data and data fields of the plurality of credit data files.
7. A computer system for pricing a security with underlying assets, the system comprising:
a computer processor;
a computer readable medium accessible by the processor; and
software stored on the computer readable medium, the software comprising:
an asset data module configured to obtain asset data relating to the underlying assets of the security, wherein the asset data is de-identified with respect to an identity of consumers associated with the underlying assets;
a credit data module configured to obtain credit-related data of consumers associated with the underlying assets of the security;
a statistical analysis module configured to generate a prediction of an occurrence of an event comprising a vector of probability of default over time for each of the underlying assets of the security, wherein the vector of probability of default comprises consumer credit histories of consumers associated with the underlying assets, wherein the consumer credit histories are obtained by matching the de-identified asset data to the credit-related data and
a security pricing module configured to utilize the vector of probability over time in pricing the security.
8. The system of claim 7 , wherein the credit-related data comprises macroeconomic trend data.
9. The system of claim 7 , wherein the security is a mortgage-related security.