Patent Issued for Methods and systems for improving the underwriting process (USPTO 11158003): Massachusetts Mutual Life Insurance Company

2021 NOV 16 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- Massachusetts Mutual Life Insurance Company (Springfield, Massachusetts, United States) has been issued patent number 11158003, according to news reporting originating out of Alexandria, Virginia, by NewsRx editors.

The patent’s inventors are Ross, Gareth (Amherst, MA, US), Walker, Tricia (East Hampton, MA, US).

This patent was filed on October 17, 2019 and was published online on October 26, 2021.

From the background information supplied by the inventors, news correspondents obtained the following quote: “Underwriting is the process that financial service providers use to determine eligibility of their costumers to receive their products (equity capital, insurance, mortgage or credit). Currently, the underwriting process may be described almost entirely as a manual process. Trained individuals, or underwriters, traditionally perform the underwriting process. The underwriting process may be very time-consuming and may involve the analysis of a plurality of underwriting standards set by a financial institution. Furthermore, the underwriting process may be biased by the judgment of the underwriter. Variation in factors such as underwriter training, experience, and quality of previous assessments may cause underwriters to make different decisions and judgments. As a result, there can be a large amount of variability and inconsistencies in the insurance underwriting process. Therefore, there is a need to improve conventional underwriting methods.”

Supplementing the background information on this patent, NewsRx reporters also obtained the inventors’ summary information for this patent: “A system and method for improving the underwriting process are disclosed. According to an embodiment, the underwriting system operates within a system architecture that includes components that dynamically interact with each other through network connections. In this embodiment, the system includes one or more client computing devices, one or more external sources, one or more internal databases, an underwriting platform, and one or more of the following software modules: analytical engine, ranking module, underwriting heuristics, and decision tools. Further to this embodiment, the system includes a user interface to interact with users (agents/underwriters) by means of a client computing device.

“According to some embodiments, a method for improving the underwriting process within an insurance company includes a plurality of steps performed by a processor. The steps include: retrieving outcome data to select and determine best underwriters; reviewing associated data that is associated with the best underwriters to understand decision and triage process; determining significance of key data elements; building a heuristic underwriting model; testing the model; and deploying decision tool within an underwriting platform.

“By executing this method through the exemplary operating environments, big data analytics and data mining techniques can be implement for a more efficient and faster processing of larger data sets. In this way, efficiencies are created by providing the financial or insurance company with ways to improve the current underwriting process. In addition, the agents/underwriters can receive automatic suggestions or checklists with valuable information before making important decisions when underwriting an applicant for one or more insurance products. These features allow performing large work such as heavy calculations and time consuming analysis in a more efficient manner than other approaches such as manual work performed by humans.

“In one embodiment, a computer-implemented method comprises determining, by a server, a subset of underwriter profiles from a set of former and current underwriter profiles based upon performance of the underwriters associated with the subset of underwriter profiles for a set of historic data obtained from an internal database; identifying, by the server, variables that are statistically similar for underwritten records associated with the subset of underwriter profiles, wherein the variables represent decision heuristics of the underwriters associated with the subset of underwriter profiles; generating, by the server, a heuristic underwriting computer model that generates a resolution based upon the identified variables that are statistically similar for underwritten records associated with the subset of underwriter profiles; and generating, by the server, a decision tool based on the heuristic underwriting computer model for an underwriting platform.

“In another embodiment, a system comprises an analytical engine server comprising a first module configured for determining, by the analytical engine server, a subset of underwriter profiles from a set of former and current underwriter profiles based upon performance of the underwriters associated with the subset of underwriter profiles for a set of historic data obtained from an internal database; a second module configured for identifying, by the analytical engine server, variables that are statistically similar for underwritten records associated with the subset of underwriter profiles, wherein the variables represent decision heuristics of the underwriters associated with the subset of underwriter profiles; a third module configured for generating, by the analytical engine server, a heuristic underwriting computer model that generates a resolution based upon the identified variables that are statistically similar for underwritten records associated with the subset of underwriter profiles; and a fourth module configured for generating, by the analytical engine server, a decision tool based on the heuristic underwriting computer model for an underwriting platform.”

The claims supplied by the inventors are:

“1. A computer-implemented method comprising: identifying, by a server, a set of existing users from an internal database, each existing user having a performance satisfying a threshold based on a set of historic data from the internal database and a set of outcome data retrieved from one or more external databases comprising at least one social networking database; training, by the server, an artificial intelligence model having a set of nodes where each node represents a decision made for previously considered customers by each user within the set of existing users and one or more attributes associated with each previously considered customer, the artificial intelligence model configured to emulate resolution patterns corresponding to processing of the previously considered customers by each user within the set of existing users; and upon receiving an input of information of a potential customer, executing, by the server, the artificial intelligence model to generate a resolution for the potential customer.

“2. The method according to claim 1, further comprising: generating, by the server, a decision tool user interface configured to implement the artificial intelligence model, wherein the decision tool user interface is configured to receive the input of information of the potential customer.

“3. The method according to claim 2, further comprising: when an inputted decision of a user interacting with the decision tool user interface differs from the resolution generated via the artificial intelligence model, displaying, by the server, an alert on the decision tool user interface before allowing the user to proceed with the decision.

“4. The method according to claim 1, wherein the generated resolution comprises a risk score calculation, a risk of loss assessment, and a risk classification for the potential customer.

“5. The method according to claim 1, further comprising: generating, by the server, a test protocol to determine a significance of each node within the set of nodes.

“6. The method according to claim 5, wherein the test protocol is based upon a life event and a selected product or service.

“7. The method according to claim 1, wherein the artificial intelligence model is based at least in part on third party data.

“8. The method according to claim 1, further comprising: generating, by the server, a hierarchical heuristic nodal network comprising the set of nodes.

“9. The method according to claim 1, further comprising: training, by the server, the artificial intelligence model utilizing a support vector machine algorithm.

“10. The method according to claim 1, further comprising: updating, by the server, the artificial intelligence model periodically based on new decisions made by the set of existing users.

“11. A system comprising: an electronic user device, and a server in communication with the electronic user device and configured to: identify a set of existing users from an internal database each existing having a performance satisfying a threshold based on a set of historic data from the internal database and a set of outcome data retrieved from one or more external databases comprising at least one social networking database; train an artificial intelligence model having a set of nodes where each node represents a decision made for previously considered customers by each user within the set of existing users and one or more attributes associated with each previously considered customer, the artificial intelligence model configured to emulate resolution patterns corresponding to processing of the previously considered customers by each user within the set of existing users; and upon receiving an input of information of a potential customer from the electronic user device, execute the artificial intelligence model to generate a resolution for the potential customer.

“12. The system according to claim 11, wherein the server is further configured to: generate a decision tool user interface on the electronic user device configured to implement the artificial intelligence model, wherein the decision tool user interface is configured to receive the input of information of the potential customer.

“13. The system according to claim 12, wherein the server is further configured to: when an inputted decision of a user interacting with the decision tool user interface differs from the resolution generated via the artificial intelligence model, display an alert on the decision tool user interface of the electronic user device before allowing the user to proceed with the decision.

“14. The system according to claim 11, wherein the generated resolution comprises a risk score calculation, a risk of loss assessment, and a risk classification for the potential customer.

“15. The system according to claim 11, wherein the server is further configured to: generate a test protocol to determine a significance of each node within the set of nodes.

“16. The system according to claim 15, wherein the test protocol is based upon a life event and a selected product or service.

“17. The system according to claim 11, wherein the artificial intelligence model is based at least in part on third party data.

“18. The system according to claim 11, wherein the server is further configured to: generate a hierarchical heuristic nodal network comprising the set of nodes.

“19. The system according to claim 11, wherein the server is further configured to: train the artificial intelligence model utilizing a support vector machine algorithm.

“20. The system according to claim 11, wherein the server is further configured to: update the artificial intelligence model periodically based on new decisions made by the set of existing users.”

For the URL and additional information on this patent, see: Ross, Gareth. Methods and systems for improving the underwriting process. U.S. Patent Number 11158003, filed October 17, 2019, and published online on October 26, 2021. Patent URL: http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PALL&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.htm&r=1&f=G&l=50&s1=11158003.PN.&OS=PN/11158003RS=PN/11158003

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