Patent Issued for Performance Estimation System Utilizing A Data Analytics Predictive Model (USPTO 10,599,670)

2020 APR 03 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- According to news reporting originating from Alexandria, Virginia, by NewsRx journalists, a patent by the inventors Peng, Jufeng (Avon, CT); Larsson, Gregory Patrick (Brooklyn, NY); Kosednar, Michael F (Overland Park, KS); Gouin, Anne S (Portland, CT), filed on April 13, 2016, was published online on April 6, 2020.

The assignee for this patent, patent number 10,599,670, is Hartford Fire Insurance Company (Hartford, Connecticut, United States).

Reporters obtained the following quote from the background information supplied by the inventors: “Electronic records, such as files and database entries, may be stored and utilized by an enterprise. Moreover, an enterprise may be interested in analyzing information about each electronic record to predict a future performance estimation value that might be associated with that particular record. For example, the enterprise might want to predict future performance estimation values to help optimize certain parameters and/or to identify electronic records that may need to be adjusted. Manually analyzing a batch of electronic records, however, can be a time consuming and error prone process--especially where there are a substantial number of records to be analyzed (e.g., thousands of electronic records might need to be reviewed) and/or there are a lot of factors that could potentially influence predictions of future performance estimation values.

“It would be desirable to provide systems and methods to automatically provide a future performance estimation assessment tool that generates faster, more accurate future performance estimation values and allows for flexibility and effectiveness when responding to those values.”

In addition to obtaining background information on this patent, NewsRx editors also obtained the inventors’ summary information for this patent: “According to some embodiments, systems, methods, apparatus, computer program code and means provide a future performance estimation assessment tool. In some embodiments, a server may access a data store containing electronic records, each electronic record representing a risk association for an entity in connection with a plurality of relationships, and each electronic record may contain a set of record characteristic values. The server may automatically designate a first sub-set of the set of record characteristic values as fixed effect variables and a second sub-set as random effect variables. A data analytics mixed effect predictive model may then generate, based on the fixed and random effect variables, a future performance estimation value for the risk association of each entity in connection with its plurality of relationships. An indication associated with the future performance estimation value for the risk association of at least one entity in connection with its plurality of relationships may then be transmitted to generate an interactive user interface display.

“Some embodiments comprise: means for accessing, by an automated back-end application computer server, a data store containing electronic records, each electronic record representing a risk association for an entity in connection with a plurality of relationships, wherein each electronic record contains a set of record characteristic values; means for automatically designating, by the back-end application computer server, a first sub-set of the set of record characteristic values as fixed effect variables; means for automatically designating, by the back-end application computer server, a second sub-set of the set of record characteristic values as random effect variables; means for generating, by a data analytics mixed effect predictive model based on the fixed effect variables and the random effect variables, a future performance estimation value for the risk association of each entity in connection with its plurality of relationships; and means for transmitting an indication associated with the future performance estimation value for the risk association of at least one entity in connection with its plurality of relationships to generate an interactive user interface display, wherein said transmitting is performed by a communication port, coupled to the back-end application computer server, that facilitates an exchange of electronic messages, via a distributed communication network, supporting the interactive user interface display.

“In some embodiments, a communication device associated with a back-end application computer server exchanges information with remote devices. The information may be exchanged, for example, via public and/or proprietary communication networks.

“A technical effect of some embodiments of the invention are improved and computerized ways to provide a future performance estimation assessment tool that generates faster, more accurate future performance estimation values and allows for flexibility and effectiveness when responding to those values. With these and other advantages and features that will become hereinafter apparent, a more complete understanding of the nature of the invention can be obtained by referring to the following detailed description and to the drawings appended hereto.”

The claims supplied by the inventors are:

“What is claimed:

“1. A system to provide a future performance estimation assessment tool for an enterprise via an automated back-end application computer server, comprising: (a) at least one internal data source storing data collected by the enterprise; (b) at least one third-party data source external to the enterprise; © a data store containing electronic records created in accordance with data from both the internal data source and the third-party data source, each electronic record representing a risk association for an entity in connection with a plurality of relationships, wherein each electronic record contains a set of record characteristic values; (d) the back-end application computer server, coupled to the data store, programmed to: (i) access the electronic records in the data store, (ii) automatically designate a first sub-set of the set of record characteristic values of each electronic record as fixed effect variables, (iii) automatically designate a second sub-set of the set of record characteristic values of each electronic record as random effect variables, (iv) generate, by a data analytics mixed effect predictive model based on the fixed effect variables and the random effect variables, a future performance estimation value for the risk association of each entity in connection with its plurality of relationships, and (v) transmit an indication associated with the future performance estimation value for the risk association of at least one entity in connection with its plurality of relationships to generate an interactive user interface display; and (e) a communication port coupled to the back-end application computer server to facilitate an exchange of electronic messages, via a distributed communication network, supporting the interactive user interface display, including a display of a plurality of the record characteristic values, component scores associated with those record characteristic values, and the future performance estimation value.

“2. The system of claim 1, wherein the future performance estimation value is further based at least in part on: (a) a generalized linear model, and (ii) a generalized linear mixed effect model.

“3. The system of claim 1, wherein the data analytics mixed effect predictive model is defined as: Y=.beta.+Zu+e where .beta. represents a fixed effect intercept, u represents a random effect predictor, e represents an error term, and X and Z represent design matrices relating observations Y to .beta. and u, respectively.

“4. The system of claim 1, wherein the future performance estimation assessment tool comprises a loss driven model calculator, and each value in the set of record characteristic value is associated with a component weighting score.

“5. The system of claim 4, wherein the loss driven model outputs a predicted loss ratio.

“6. The system of claim 4, wherein the component weighting scores are associated with a Weight of Evidence (“WoE”) transformation.

“7. The system of claim 1, wherein each entity is associated with an employer, the plurality of relationships are a plurality of employer-employee relationships, and the risk association is an employment practices liability insurance policy that policy protects the employer against claims from employees in connection with alleged wrongful acts arising from the employment process, including claims associated with: (i) discrimination, (ii) harassment, (iii) retaliation, (iv) violation of a governmental employment regulation or statute, (v) wrongful discipline, (vi) wrongful failure to promote, and (vii) wrongful termination.

“8. The system of claim 7, wherein the data analytics mixed effect predictive model is associated with a generalized linear mixed effect model that has: insurance policy information as a fixed effect predictor model input, geographic metropolitan area data as a random effect predictor model input, and risk estimates as a model output.

“9. The system of claim 7, wherein at least some of the set of record characteristic values are associated with insurance policy data, including at least one of: (i) an insurance policy length, (ii) a deductible amount, (iii) a coverage limit, and (iv) a deductible self-insured retention amount.

“10. The system of claim 7, wherein at least some of the set of record characteristic values are associated with employer data, including at least one of: (i) a number of employees, (ii) a number of employees, (iii) employee turnover data, (iv) an average cost per employee by employer size, (v) industry category, (vi) a number of claims, (vii) a company financial score, (viii) one or more human resources policies that are or will be in effect, (ix) tenure data, (x) a public or private business indicator, (xi) Equal Employment Opportunity Commission (“EEOC”) charges, (xii) a new business indicator, and (xiii) an amount of time in business indicator.

“11. The system of claim 7, wherein at least some of the set of record characteristic values are associated with geographic data, including at least one of: (i) a country, (ii) a county, (iii) a ZIP code, (iv) a state grouping, (v) local unemployment data, (vi) local Equal Employment Opportunity Commission (“EEOC”) charges, (vii) local per-capita lawyer and litigation climate data, and (viii) local census information.

“12. The system of claim 7, wherein at least some of the set of record characteristic values are associated with third-party data, including at least one of: (i) a financial score, (ii) social media information, (iii) economic indicators, and (iv) macro-economic conditions.

“13. The system of claim 7, wherein at least some of the set of record characteristic values are associated with other types of insurance, including at least one of: (i) workers’ compensation insurance, (ii) disability insurance, and (iii) general liability insurance.

“14. The system of claim 1, wherein future performance estimation values are associated with a geographic metropolitan risk analysis.

“15. The system of claim 1, wherein future performance estimation values are associated with a portfolio risk flag that uses using third-party economic indicators to help monitor macro-economic conditions for risk and assess growth objectives as follows: Risk Flag=w.sub.1*US_LEI+w.sub.2*US_CEI wherein w.sub.1 and w.sub.2 are weighting factors, US_LEI is associated with a United States leading economic indicator and US_CEI is associated with a United States coincident economic indicator.

“16. The system of claim 1, wherein each electronic record is associated with a record identifier and a communication address, and the sets of record characteristic values are collected via at least one of: (i) sending a communication to a communication address and receiving, from a party associated with an electronic record having that communication address, a response to the communication, (ii) a postal mailing automatically generated by a distribution center, (iii) a postal mailing received by the distribution center, (iv) an email automatically generated by an email server, (v) information provided a web interface, (vi) an interactive voice response system associated with a telephone call center, (vii) a chat application that interacts with a party in substantially real time, and (viii) a video link.

“17. The system of claim 1, wherein, after the future performance estimation values are generated, the back-end application computer server is further to periodically monitor performance outcomes and automatically adjust the data analytics mixed effect predictive model.

“18. A computerized method to provide a future performance estimation assessment tool via an automated back-end application computer server, comprising: accessing, by the automated back-end application computer server, a data store containing electronic records, each electronic record representing a risk association for an entity in connection with a plurality of relationships, wherein each electronic record contains a set of record characteristic values; automatically designating, by the back-end application computer server, a first sub-set of the set of record characteristic values of each electronic record as fixed effect variables; automatically designating, by the back-end application computer server, a second sub-set of the set of record characteristic values of each electronic record as random effect variables; generating, by a data analytics mixed effect predictive model based on the fixed effect variables and the random effect variables, a future performance estimation value for the risk association of each entity in connection with its plurality of relationships; and transmitting an indication associated with the future performance estimation value for the risk association of at least one entity in connection with its plurality of relationships to generate an interactive user interface display, wherein said transmitting is performed by a communication port, coupled to the back-end application computer server, that facilitates an exchange of electronic messages, via a distributed communication network, supporting the interactive user interface display.

“19. A non-tangible, computer-readable medium storing instructions, that, when executed by a processor, cause the processor to perform a method to provide a future performance estimation assessment tool via an automated back-end application computer server, the method comprising: accessing, by the automated back-end application computer server, a data store containing electronic records, each electronic record representing a risk association for an entity in connection with a plurality of relationships, wherein each electronic record contains a set of record characteristic values; automatically designating, by the back-end application computer server, a first sub-set of the set of record characteristic values of each electronic record as fixed effect variables; automatically designating, by the back-end application computer server, a second sub-set of the set of record characteristic values of each electronic record as random effect variables; generating, by a data analytics mixed effect predictive model based on the fixed effect variables and the random effect variables, a future performance estimation value for the risk association of each entity in connection with its plurality of relationships; and transmitting an indication associated with the future performance estimation value for the risk association of at least one entity in connection with its plurality of relationships to generate an interactive user interface display, wherein said transmitting is performed by a communication port, coupled to the back-end application computer server, that facilitates an exchange of electronic messages, via a distributed communication network, supporting the interactive user interface display including an automatic display of an alert signal when it is determined that the data analytics mixed effect predictive model is not generating appropriate future performance estimation values.”

For more information, see this patent: Peng, Jufeng; Larsson, Gregory Patrick; Kosednar, Michael F; Gouin, Anne S. Performance Estimation System Utilizing A Data Analytics Predictive Model. U.S. Patent Number 10,599,670, filed April 13, 2016, and published online on April 6, 2020. 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=10,599,670.PN.&OS=PN/10,599,670RS=PN/10,599,670

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