Systems and methods for detecting bust out fraud using credit data
AssigneeExperian Information Solutions, Inc.
InventorsHakan Olof Brunzell, Arielle Renee Caron, Tak Wun Wong, Anthony J. Sumner
Life of this patent
Estimating the term…
Abstract
Systems and methods are for, for example, predicting bust out fraud using credit bureau data. In one embodiment, credit bureau scoring models are created using credit bureau data to detect bust out fraud. The credit bureau scoring models may be then applied to consumer data to determine whether a consumer is involved in bust out fraud.
Claims18
A method of detecting bust out accounts, wherein bust out accounts exhibit a consumer opening one or more credit accounts across one or more credit issuers and initially exhibiting normal consumer behavior followed by a large number of purchases, cash advances, or other uses of credit before abandonment of the one or more accounts, the method comprising:
- accessing, by a computing system, consumer data associated with a consumer;
- accessing a bust out scoring model from a storage repository, the bust out scoring model created using credit bureau data and at least one consumer characteristic statistically correlated with predicting bust out accounts;
- and
- periodically applying, using the computing system, the bust out scoring model to the consumer data of the consumer to generate a bust out score for the consumer, wherein the periodically applying the bust out scoring model comprises performing the following method on a periodic basis:
- accessing, by the computer system, updated consumer data associated with the consumer;
- applying, by the computer system, the bust out scoring model to the updated consumer data to generate the bust out score for the consumer;
- determining, by the computer system, whether the updated consumer data exhibits characteristics of bust out accounts by comparing the bust out score to a threshold level;
- and
- in response to the determining that the bust out score associated with the consumer is below the threshold level, providing, by the computing system, an indication to a user indicating that no bust out account has been detected;
- in response to the determining that the bust out score associated with the consumer is at or above the threshold level, providing, by the computing system, an indication to the user indicating that a potential bust out account has been detected.
A method of detecting bust out accounts, wherein bust out accounts exhibit a consumer opening one or more credit accounts across one or more credit issuers and initially exhibiting normal consumer behavior followed by a large number of purchases, cash advances, or other uses of credit before abandonment of the one or more accounts, the method comprising:
- accessing, by a computing system, consumer data associated with a consumer;
- accessing a bust out scoring model from a storage repository, the bust out scoring model created using credit bureau data and at least one consumer characteristic statistically correlated with predicting bust out accounts;
- and
- periodically applying, using the computing system, the bust out scoring model to the consumer data of the consumer to generate a bust out score for the consumer, wherein the periodically applying the bust out scoring model comprises performing the following method on a periodic basis:
- accessing, by the computer system, updated consumer data associated with the consumer;
- applying, by the computer system, the bust out scoring model to the updated consumer data to generate the bust out score for the consumer, wherein the bust out score is configured for comparison to a threshold level in order to determine whether the updated consumer data exhibits characteristics of bust out accounts.
A bust out accounts detection system, wherein bust out accounts exhibit a consumer opening one or more credit accounts across one or more credit issuers and initially exhibiting normal consumer behavior followed by a large number of purchases, cash advances, or other uses of credit before abandonment of the one or more accounts, the system comprising:
- a computer processor configured to execute modules comprising at least:
- a data acquisition module configured to periodically access consumer data associated with a consumer;
- a bust out fraud detection module configured to access a bust out scoring model from a storage repository and to periodically apply the bust out scoring model to the consumer data to generate a bust out score for the consumer, the bust out scoring model created using credit bureau data and at least one consumer characteristic statistically correlated with predicting bust out accounts;
- and
- a reporting module configured to perform the following method on a periodic basis:
- accessing through the data acquisition module updated consumer data associated with the consumer;
- applying through the bust out fraud detection module the bust out scoring model to the updated consumer data to generate the bust out score for the consumer, wherein the bust out score is configured for comparison to a threshold level in order to determine whether the consumer data exhibits characteristics of bust out accounts.
Dependencies are inferred from the claim text.