Patent Issued for Fraud detection using augmented analytics (USPTO 11544713): United Services Automobile Association

2023 JAN 19 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- A patent by the inventors Bell, Curtis M. (San Antonio, TX, US), Buentello, Andre R. (San Antonio, TX, US), Hansen, Gregory D. (San Antonio, TX, US), Huggar, Stacy C. (San Antonio, TX, US), Khmelev, Yevgeniy (San Antonio, TX, US), Kwak, Victor (Frisco, TX, US), Lyle, Ruthie (Durham, NC, US), McEachron, Jon D. (Boerne, TX, US), Medina, III, Reynaldo (San Antonio, TX, US), Philbrick, Ashley R. (San Antonio, TX, US), Romero, Jr., Jose L. (San Antonio, TX, US), filed on September 30, 2020, was published online on January 3, 2023, according to news reporting originating from Alexandria, Virginia, by NewsRx correspondents.

Patent number 11544713 is assigned to United Services Automobile Association (San Antonio, Texas, United States).

The following quote was obtained by the news editors from the background information supplied by the inventors: “Ever larger amounts of data are available to businesses and their customers. Some may come through deliberate entry or submission and retention. Other can be collected passively through the vast array of networked devices and communication channels available today. Users’ locations, activities, purchasing habits, communication, et cetera, can all be aggregated when permissions are granted to access and share data. This information is dramatically more complex and fulsome than information routinely utilized in, e.g., actuarial data sets.

“While a great deal of resources are committed to collecting, communicating, and aggregating this data, it is not always useful. It is overwhelming to any human observer. To begin to grasp information therein, computers have been utilized. However, it is not well understood how to best harness the use of computers in this regard.

“Fraud detection remains a challenge and results in dramatic losses for financial service companies. As sensors and network connections proliferate, volumes of data are becoming available that could be used to identify new factors or combinations of factors that are suggestive of fraud. It would be beneficial to develop a system that could identify real-time transactions involving fraud risk, particularly relating to previously undiscovered correlations which may be discoverable through machine learning.

“One aspect which could be improved is the prediction and reduction of, or adjustment for, fraud in real-time transactions. There is a need for new techniques to utilize data to improve and increase efficiency in fraud avoidance.”

In addition to the background information obtained for this patent, NewsRx journalists also obtained the inventors’ summary information for this patent: “The needs existing in the field are addressed by the present disclosure, which relates to systems, methods, and computer usable media for predicting and reducing or avoiding fraud.

“In an embodiment, a method comprises ingesting fraud data related to a fraud event. The fraud data includes contextual data describing context surrounding the fraud event, and the fraud data is ingested to an individual record associated with an entity involved in the fraud event, and wherein the individual record has a record format. The method also comprises ingesting real-time transaction data, wherein the real-time transaction data includes data describing a requested transaction and transactional contextual data associated with the requested transaction. The method also comprises determining whether a correlation match exists between the fraud data and the real-time transaction data and causing an action to close the real-time transaction associated with the real-time transaction data based on the correlation match. Closing the real-time transaction includes causing completion of the real-time transaction when the correlation match does not exist, and closing the real-time transaction includes freezing the real-time transaction when the correlation match exists.

“In another embodiment, a system comprises a non-transitory computer-readable medium storing instructions. The instructions are configured to effectuate a data ingestion component configured to ingest fraud data related to a fraud event and real-time transaction data related to a real-time transaction request, wherein the fraud data includes contextual data describing context surrounding the fraud event, wherein the real-time transaction data includes data describing a requested transaction and transactional contextual data associated with the requested transaction, wherein the fraud data is ingested to an individual record associated with an entity involved in the fraud event, and wherein the individual record has a record format. The instructions are configured to effectuate a correlation component configured determine whether a correlation match exists between the fraud data and the real-time transaction data. The instructions are also configured to effectuate a user interface configured to provide a notification based on the correlation.

“This summary is intended to provide a short description of some aspects only. Additional and alternative details will be apparent on review of other portions of this disclosure.”

The claims supplied by the inventors are:

“1. A method, comprising: ingesting fraud data related to fraud events, wherein the fraud data includes contextual data describing context surrounding the fraud events, wherein the fraud data respectively associated with each of the fraud events is ingested to an individual record associated with an entity involved in the respective fraud event, and wherein the individual record has a record format; ingesting transaction data, wherein the transaction data includes data describing transactions and transactional contextual data associated with the transactions; determining a plurality of correlations between the fraud data and the transaction data using unsupervised machine learning of the individual record; analyzing the plurality of correlations using supervised machine learning to identify at least one causative correlation; receiving real-time transaction data, wherein the real-time transaction data includes data describing a requested transaction and real-time transactional contextual data associated with the requested transaction; determining whether a fraud correlation match exists for the requested transaction based on the real-time transaction data corresponding to at least one of the at least one causative correlation; and causing an action to close the real-time transaction associated with the real-time transaction data based on the fraud correlation match, wherein closing the real-time transaction includes causing completion of the real-time transaction when the correlation match does not exist, and wherein closing the real-time transaction includes freezing the real-time transaction when the fraud correlation match exists.

“2. The method of claim 1, comprising: providing a notification that the real-time transaction has been frozen.

“3. The method of claim 1, comprising: determining a context difference between the fraud data and the contextual data; and determining an action to reconcile the context difference.

“4. The method of claim 1, comprising: preparing at least one of the fraud data and the real-time transaction data according to the record format.

“5. The method of claim 1, wherein machine learning identifies one or more fields of the record format to be populated by the fraud data and the real-time transaction data, and wherein the record format is dynamically updated based on identification of a new field type by the machine learning.

“6. The method of claim 1, comprising: discarding, using supervised machine learning, at least one of the plurality of correlations based on the at least one of the plurality of correlations being non-causative.

“7. The method of claim 1, comprising: causing an incentive to be offered to a party associated with the requested transaction based on the party completing a behavior that eliminates the fraud correlation match.

“8. A system, comprising a non-transitory computer-readable medium storing instructions configured to effectuate: a data ingestion component configured to ingest fraud data related to fraud events and transaction data related to transactions, wherein the fraud data includes contextual data describing context surrounding the fraud events, wherein the transaction data includes real-time transaction data, wherein real-time transaction data among the transaction data includes data describing a requested transaction and transactional contextual data associated with the requested transaction, wherein the fraud data associated with each of the fraud events is ingested to an individual record associated with an entity involved in the re iv fraud event, and wherein the individual record has a record format; an unsupervised machine learning component configured to determine a plurality of correlations between the fraud data and the transaction data using unsupervised machine learning of the individual record; a supervised machine learning component configured to analyze the plurality of correlations using supervised machine learning to identify at least one causative correlation; a correlation component configured to determine whether a fraud correlation match exists for the requested transaction based on the real-time transaction data corresponding to at least one of the at least one causative correlation; and a user interface configured to provide a notification based on the correlation.

“9. The system of claim 8, wherein the correlation component is configured to cause an action to close the real-time transaction associated with the real-time transaction data based on the fraud correlation match, wherein closing the real-time transaction includes causing completion of the real-time transaction when the fraud correlation match does not exist, and wherein closing the real-time transaction includes freezing the real-time transaction when the fraud correlation match exists.

“10. The system of claim 9, wherein the instructions are further configured to effectuate: a transaction approval component configured to complete the real-time transaction or freeze the real-time transaction based on the fraud correlation match.

“11. The system of claim 8, wherein the instructions are further configured to effectuate: a data preparation component configured to prepare at least one of the fraud data and the real-time transaction data according to the record format.

“12. The system of claim 8, wherein the instructions are further configured to effectuate: a fraud detection database.

“13. The system of claim 8, wherein the correlation component is configured to determine a context difference between the fraud data and the contextual data.

“14. The system of claim 13, wherein the correlation component is configured to determine an action to reconcile the context difference.

“15. A non-transitory computer-readable medium storing instructions that when executed by a processor effectuate operations comprising: ingesting fraud data related to fraud events, wherein the fraud data includes contextual data describing context surrounding the fraud events, wherein the fraud data associated with each of the fraud events is ingested to an individual record associated with an entity involved in the respective fraud event, and wherein the individual record has a record format; ingesting transaction data, wherein the transaction data includes data describing transactions and transactional contextual data associated with the transactions; determining a plurality of correlations between the fraud data and the transaction data using unsupervised machine learning of the individual record; analyzing the plurality of correlations using supervised machine learning to identify at least one causative correlation; receiving real-time transaction data, wherein the real-time transaction data includes data describing a requested transaction and real-time transactional contextual data associated with the requested transaction; determining whether a fraud correlation match exists for the requested transaction based on the real-time transaction data corresponding to at least one of the at least one causative correlation; and causing an action to close the real-time transaction associated with the real-time transaction data based on the fraud correlation match, wherein closing the real-time transaction includes causing completion of the real-time transaction when the fraud correlation match does not exist, and wherein closing the real-time transaction includes freezing the real-time transaction when the fraud correlation match exists.

“16. The non-transitory computer-readable medium of claim 15, wherein the instructions when executed effectuate operations comprising: providing a notification that the real-time transaction has been frozen.

“17. The non-transitory computer-readable medium of claim 15, wherein the instructions when executed effectuate operations comprising: determining a context difference between the fraud data and the contextual data.

“18. The non-transitory computer-readable medium of claim 17, wherein the instructions when executed effectuate operations comprising: determining an action to reconcile the context difference.

“19. The non-transitory computer-readable medium of claim 15, wherein machine learning identifies one or more fields of the record format to be populated by the fraud data and the real-time transaction data.

“20. The non-transitory computer-readable medium of claim 19, wherein the record format is dynamically updated based on identification of a new field type by the machine learning.”

URL and more information on this patent, see: Bell, Curtis M. Fraud detection using augmented analytics. U.S. Patent Number 11544713, filed September 30, 2020, and published online on January 3, 2023. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11544713)&db=USPAT&type=ids

(Our reports deliver fact-based news of research and discoveries from around the world.)