“Systems and Methods for Computerized Loss Scenario Modeling and Data Analytics” in Patent Application Approval Process (USPTO 20220383422): Insurance Services Office Inc.

2022 DEC 19 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- A patent application by the inventors Conde, Rafael (Clifton, NJ, US); Hulett, Jim (St. Pete, FL, US); Townsend, Douglas (Wantagh, NY, US), filed on May 26, 2022, was made available online on December 1, 2022, according to news reporting originating from Washington, D.C., by NewsRx correspondents.

This patent application is assigned to Insurance Services Office Inc. (Jersey City, New Jersey, United States).

The following quote was obtained by the news editors from the background information supplied by the inventors: “

“Technical Field

“The present disclosure relates generally to the field of data modeling and analytics. More specifically, the present disclosure relates to systems and methods for computerized loss scenario modeling and data analytics.

“Related Art

“In today’s machine learning and artificial intelligence fields, there is a desire to exploring sophisticated computerized approaches for conducting insurance fraud analytics. For example, neural networks, machine learning, multivariate random forest models, and other techniques are being explored to create modern fraud detection models. These techniques can produce accurate predictive results and detect complex fraud patterns. However, these sophisticated fraud models can also be overly complex and can present practical challenges when operationalized by a special investigation unit (SIU).

“Further, high expectations of the sophisticated fraud models can be deflated, and confidence can be lost if only nebulous or unintuitive reasons support a scored claim. Also, an SIU team might have varying degrees of understanding or trust in the advanced predictive models based on its own experiences. Often, the more sophisticated the modeling technique, the more challenging it is to provide understandable fraud scenarios and overall context for end users. This challenge is rooted in the complex nature of advanced analytic techniques and multivariate approaches that make it difficult to surface meaningful reason codes.

“Furthermore, a fraud detection model may include data from only an individual insurance carrier and, consequently, can produce thin, incomplete results. This lack of industry data can be especially challenging for analytics linked to loss on newer business. Further still, data scientists using traditional empirical approaches may not consider critical investigative concepts or engage the right business subject matter experts to understand the meaning of analytical output.

“Accordingly, what would be desirable, but have not yet been provided, are systems and methods which solve the foregoing and other needs.”

In addition to the background information obtained for this patent application, NewsRx journalists also obtained the inventors’ summary information for this patent application: “The present disclosure relates to systems and methods for computerized loss scenario modeling and data analytics to identify questionable insurance claims that require further investigation. Specifically, the present disclosure includes systems and methods for providing customized claim loss analytics including a database for storing claims data related to one or more loss events and a front-end processor in communication with the claims database. The front end processor retrieves the claims data from the claims database. The front-end processor also generates a front-end user interface with a plurality of user elements configured to allow a user to select one or more business rules and one or more data points for a custom loss scenario rule and generates the custom loss scenario rule based on the user input. The front-end processor then transmits the custom loss scenario rule to a primary claims analytics processor for implementation into a production data flow process.

“According to embodiments of the present disclosure, the primary claims analytics processor retrieves the claims data from the database, determines a propensity score for the claims data, and identifies one or more existing business rules triggered by the claims data. The front-end processor can then retrieve the propensity score for the claims data and the existing triggered business rules from the primary claims analytics processor, which the front end processor can display in the front-end user interface. The existing triggered business rules can then be included in the custom loss scenario rule.

“According to further embodiments of the present disclosure, the production data flow process includes applying one or more fraud detection algorithms to detect one or more fraud patterns in the claims data and implementing the custom loss scenario rule into the production data flow process causes the detection of the fraud patterns to be extended.

“According to still further embodiments of the present disclosure, the front-end user interface also includes a plurality of user elements that are configured to allow the user to modify or delete a saved custom loss scenario rule.”

The claims supplied by the inventors are:

“1. A system for customized claim loss analytics, comprising: a database for storing claims data related to one or more loss events; and a front-end processor in communication with the claims database, the front end processor: retrieving the claims data from the claims database; generating a front-end user interface with a plurality of user elements configured to allow a user to select one or more business rules and one or more data points for a custom loss scenario rule; receiving user input related to the selection of the one or more business rules and one or more data points for the custom loss scenario rule; generating the custom loss scenario rule based on the user input; and transmitting the custom loss scenario rule to a primary claims analytics processor for implementation into a production data flow process.

“2. The system of claim 1, wherein the primary claims analytics processor retrieves the claims data from the database.

“3. The system of claim 2, wherein the primary claims analytics processor determines a propensity score for the claims data.

“4. The system of claim 3, wherein the primary claims analytics processor identifies one or more existing business rules triggered by the claims data.

“5. The system of claim 4, wherein the front-end processor retrieves the propensity score for the claims data and the one or more identified existing business rules triggered by the claims data from the primary claims analytics processor.

“6. The system of claim 5, wherein the front-end processor displays the propensity score for the claims data and the one or more identified existing business rules triggered by the claims data in the front-end user interface.

“7. The system of claim 6, wherein the custom loss scenario rule includes one or more of the identified existing business rules triggered by the claims data.

“8. The system of claim 1, wherein the production data flow process includes applying one or more fraud detection algorithms to detect one or more fraud patterns in the claims data.

“9. The system of claim 2, wherein implementation of the custom loss scenario rule into the production data flow process caused the detection of the one or more fraud patterns to be altered.

“10. The system of claim 1, wherein the front-end user interface includes a plurality of user elements configured to allow the user to modify a saved custom loss scenario rule.

“11. A method for customized loss analytics, comprising: providing a database for storing claims data related to one or more loss events; and providing a front-end processor in communication with the claims database, the front end processor: retrieving the claims data from the claims database; generating a front-end user interface with a plurality of user elements configured to allow a user to select one or more business rules and one or more data points for a custom loss scenario rule; receiving user input related to the selection of the one or more business rules and one or more data points for the custom loss scenario rule; generating the custom loss scenario rule based on the user input; and transmitting the custom loss scenario rule to a primary claims analytics processor for implementation into a production data flow process.

“12. The method of claim 11, comprising the step of retrieving by the primary claims analytics processor the claims data from the database.

“13. The method of claim 12, comprising the step of determining by the primary claims analytics processor a propensity score for the claims data.

“14. The method of claim 13, comprising the step of identifying by the primary claims analytics processor one or more existing business rules triggered by the claims data.

“15. The method of claim 14, comprising the step of retrieving by the front-end processor the propensity score for the claims data and the one or more identified existing business rules triggered by the claims data from the primary claims analytics processor.

“16. The method of claim 15, comprising the step of displaying by the front-end processor the propensity score for the claims data and the one or more identified existing business rules triggered by the claims data in the front-end user interface.

“17. The method of claim 16, wherein the custom loss scenario rule includes one or more of the identified existing business rules triggered by the claims data.

“18. The method of claim 11, wherein the production data flow process comprises the step of applying one or more fraud detection algorithms to detect one or more fraud patterns in the claims data.

“19. The method of claim 12, wherein implementation of the custom loss scenario rule into the production data flow process causes the detection of the one or more fraud patterns to be altered.

“20. The method of claim 11, wherein the front-end user interface includes a plurality of user elements configured to allow the user to modify a saved custom loss scenario rule.”

URL and more information on this patent application, see: Conde, Rafael; Hulett, Jim; Townsend, Douglas. Systems and Methods for Computerized Loss Scenario Modeling and Data Analytics. U.S. Patent Application Number 20220383422, filed May 26, 2022 and posted December 1, 2022. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(20220383422)&db=US-PGPUB&type=ids

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