Patent Issued for Determining geocoded region based rating systems for decisioning outputs (USPTO 11710186): Allstate Insurance Company
2023 AUG 15 (NewsRx) -- By a
The assignee for this patent, patent number 11710186, is
Reporters obtained the following quote from the background information supplied by the inventors: “Service providers often rely on geographical territories to provide pricing for various services. Generally, such territories are based on postal zone improvement plan (ZIP) codes. In some instances, the territories may be based on rectangular grids based on geolocation data. Once the territories are defined, they are generally not modified to when re-evaluating costs of services.
“Postal ZIP codes facilitate delivery of mail and/or packages by the postal service, and/or other delivery services. However, postal ZIP codes are not aligned with other rating factors that may be used to determine costs associated with services. For example, a postal ZIP code may include a large number of properties with differing profiles. Also, for example, rectangular grids are generally fixed in size and may not capture various related factors. Utilization of geographic regions may change over time. For example, rural areas may become suburban, new highways may be constructed, areas may be devastated by disasters, natural or man-made, and/or one or more related factors may change. Accordingly, determining rating factors based on fixed geographical regions, such as, for example, geographical regions represented by a postal ZIP code, or a rectangular grid, may not be suitable for all services.”
In addition to obtaining background information on this patent, NewsRx editors also obtained the inventors’ summary information for this patent: “In light of the foregoing background, the following presents a simplified summary of the present disclosure in order to provide a basic understanding of some aspects of the invention. This summary is not an extensive overview of the invention. It is not intended to identify key or critical elements of the invention or to delineate the scope of the invention. The following summary merely presents some concepts of the invention in a simplified form as a prelude to the more detailed description provided below.
“Aspects of the disclosure address one or more of the issues mentioned above by disclosing methods, computer readable storage media, software, systems, and apparatuses for determining geocoded regions for rating systems.
“In some aspects, a geocoded territory rating system may include a geocoded territory rating data processing system and a geocoded territory rating data analysis system. The geocoded territory rating system may include at least one processor and a memory unit storing computer-executable instructions. In some embodiments, the computer-executable instructions may be stored in one or more non-transitory computer-readable media. The geocoded territory rating system may be configured to, in operation, determine, for a geographic region and via a computing device and based on geolocation data, a plurality of sub-regions, where each sub-region of the plurality of sub-regions may include real properties with a shared profile. The geocoded territory rating system may be configured to, in operation, associate, with each sub-region, a collection of coordinate pairs, where each coordinate pair comprises a latitude and a longitude, and the collection describes a boundary of a geometric shape corresponding to the sub-region. The geocoded territory rating system may be configured to, in operation, associate, with the geographic region, geometric shapes corresponding to the plurality of sub-regions in the geographic region. The geocoded territory rating system may be configured to, in operation, associate, with each geometric shape, a rating factor for the real properties located within the sub-region corresponding to the geometric shape. The geocoded territory rating system may be configured to, in operation, store, in a database, the geometric shapes and the associated rating factors. The geocoded territory rating system may be configured to, in operation, generate, based on the rating factor and for the real properties located within the sub-region, an output. The geocoded territory rating system may be configured to, in operation, provide, via the computing device and based on the geometric shape, the generated output.
“In some aspects, the geocoded territory rating system may be configured to, in operation, receive, via the computing device, a request for an available recommendation associated with a property, where the request includes an address associated with the property. In some arrangements, the geocoded territory rating system may be configured to, in operation, convert the address to address coordinates comprising a latitude and a longitude, where the address coordinates correspond to a geolocation of the property. In some aspects, the geocoded territory rating system may be configured to, in operation, match, based on comparisons with the collections of coordinate pairs, the address coordinates with a geometric shape. In some arrangements, the geocoded territory rating system may be configured to, in operation, retrieve, based on the geometric shape, the associated rating factor. In some aspects, the geocoded territory rating system may be configured to, in operation, provide, in response to the request and via a graphical user interface and based on the rating factor, the generated output indicating the available recommendation.
“In some aspects, the geocoded territory rating system may be configured to, in operation, associate a timestamp with the shape file, and the generated output may be based on the timestamp.”
The claims supplied by the inventors are:
“1. A method comprising: training a machine learning model to determine a plurality of sub-regions using rating factors obtained for training; determining, for a geographic region and via a geocoding application of a geocoded territory rating system, the plurality of sub-regions using the trained machine learning model, wherein each sub-region of the plurality of sub-regions comprises real properties with a shared profile; associating, with each sub-region, a collection of coordinate pairs, wherein each coordinate pair comprises a latitude and a longitude, and the collection describes a boundary of a geometric shape corresponding to the sub-region, wherein determining each sub-region comprises determining a customized shape as the geometric shape using the trained machine learning model by identifying patterns associated with neighborhoods, and wherein the trained machine learning model is configured to output shape files including the geometric shapes, each shape file being associated with a different region profile; associating, with the geographic region, the geometric shapes corresponding to the plurality of sub-regions in the geographic region; associating, with each geometric shape in the shape file, a rating factor for the real properties located within the sub-region corresponding to the geometric shape; storing, in a database, the geometric shapes and the associated rating factors; generating, based on the rating factor and for the real properties located within the sub-region, an output; and providing, via the geocoded territory rating system and based on the geometric shape, the generated output.
“2. The method of claim 1, further comprising: receiving, via the geocoded territory rating system, a request for an available recommendation associated with a property, wherein the request includes an address associated with the property; converting the address to address coordinates comprising a latitude and a longitude, wherein the address coordinates correspond to a geolocation of the property; matching, based on comparisons with the collections of coordinate pairs, the address coordinates with the geometric shape; retrieving, based on the geometric shape, the associated rating factor; and in response to the request, providing, via a graphical user interface and based on the rating factor, the generated output indicating the available recommendation.
“3. The method of claim 1, further comprising: associating a timestamp with the geometric shape, and wherein the generated output is based on the timestamp.
“4. The method of claim 1, further comprising: determining, for the geographic region, a second plurality of sub-regions; updating geometric shapes corresponding to the second plurality of sub-regions; updating the geometric shape; applying a second timestamp to the geometric shape; and updating the rating factors.
“5. The method of claim 4, wherein the generated output is based on the second timestamp.
“6. The method of claim 1, wherein the generated output comprises a recommendation for: a residential insurance product, a commercial insurance product, a vehicular insurance product, an insurance underwriting process, a marketing strategy, or a type of field deployment.
“7. The method of claim 1, wherein at least one of the geometric shapes corresponds to a sub-region associated with a postal code.
“8. The method of claim 1, wherein at least one of the geometric shapes corresponds to a sub-region associated with a rectangular grid based on geolocation data.
“9. The method of claim 1, wherein the shared profile comprises at least one of a type of the real properties, a value of the real properties, a neighborhood crime rate, proximity to a body of water, proximity to a golf course, proximity to public transportation, location in a region prone to a natural disaster, position relative to a highway, or position relative to a mountain.
“10. An apparatus, comprising: a processor; and a memory unit storing computer-executable instructions, which when executed by the processor, cause the apparatus to: training a machine learning model to determine a plurality of sub-regions using a regional association of rating factors obtained for training; determining, for a geographic region and via a geocoding application of a geocoded territory rating system, the plurality of sub-regions using the trained machine learning model, wherein each sub-region of the plurality of sub-regions comprises real properties with a shared profile; associating, with each sub-region, a collection of coordinate pairs, wherein the collection describes a boundary of a geometric shape corresponding to the sub-region, wherein determining each sub-region comprises determining a customized shape as the geometric shape using the trained machine learning model by identifying patterns associated with neighborhoods, and wherein the trained machine learning model is configured to output shape files including the geometric shapes, each shape file being associated with a different region profile; receive a request for a recommendation associated with a property, wherein the request includes an address associated with the property; convert the address to address coordinates comprising a latitude and a longitude, wherein the address coordinates correspond to a geolocation of the property; match the address coordinates with one of the geometric shapes corresponding to the plurality of sub-regions; retrieve, based on the one of the geometric shapes, an associated rating factor; and in response to the request, provide, via a graphical user interface and based on the rating factor, an indication of an available recommendation.
“11. The apparatus of claim 10, wherein the instructions to match the address coordinates comprise additional computer-executable instructions, when executed by the processor, cause the apparatus to: compare the address coordinates with the collection of coordinate pairs.
“12. The apparatus of claim 10, wherein the computer-executable instructions, when executed by the processor, cause the apparatus to: associate a timestamp with each of the geometric shapes, wherein the indication of the available recommendation is based on the timestamp.
“13. The apparatus of claim 10, wherein the computer-executable instructions, when executed by the processor, cause the apparatus to: update the one of the geometric shapes; update the rating factor; and associate a second timestamp with the geometric shape, wherein the indication of the available recommendation is based on the second timestamp.
“14. The apparatus of claim 10, wherein the recommendation is for: a residential insurance product, a commercial insurance product, a vehicular insurance product, an insurance underwriting process, a marketing strategy, or a type of field deployment.
“15. The apparatus of claim 10, wherein the shared profile comprises at least one of a type of the real properties, a value of the real properties, a neighborhood crime rate, proximity to a body of water, proximity to a golf course, proximity to public transportation, location in a region prone to a natural disaster, position relative to a highway, and position relative to a mountain.
“16. One or more non-transitory computer-readable media storing instructions that, when executed by a geocoded territory rating system, cause the geocoded territory rating system to: train a machine learning model to determine a plurality of sub-regions using rating factors obtained for training; determine, for a geographic region and via a geocoding application of the geocoded territory rating system, the plurality of sub-regions using a trained machine learning model, wherein each sub-region of the plurality of sub-regions comprises real properties with a shared profile; associate, with each sub-region, a collection of coordinate pairs, wherein each coordinate pair comprises a latitude and a longitude, and the collection describes a boundary of a geometric shape corresponding to the sub-region, wherein determining each sub-region comprises determining a customized shape as the geometric shape using the trained machine learning model by identifying patterns associated with the plurality of sub-regions, and wherein the trained machine learning model is configured to output shape files including the geometric shapes, each shape file being associated with a different region profile; associate, with the geographic region, geometric shapes corresponding to the plurality of sub-regions in the geographic region; associate, with each geometric shape, a timestamp, and a rating factor associated with the timestamp, wherein the rating factor is for a product available for the real properties located within the sub-region corresponding to the geometric shape; store, in a database, the geometric shapes, the associated timestamps, and the associated rating factors; generate, for each geometric shape and based on the rating factor, an output; and provide, based on the associated timestamp, the generated output.”
For more information, see this patent: Fesenmeyer, Jonathan. Determining geocoded region based rating systems for decisioning outputs.
(Our reports deliver fact-based news of research and discoveries from around the world.)
Murdaugh accomplice Cory Fleming sentenced to 46 months in prison
Closure of Pittsburgh coal-processing plant tied to local health gains: NYU Langone Health / NYU Grossman School of Medicine
Advisor News
- 4 things every federal worker should do to safeguard their benefits
- Six steps to turn HNW friends into clients
- The two-bucket investment approach to making money last
- Republicans confront difficult Medicaid choices in search of savings to help pay for tax cuts
- Economy showing momentum despite uncertainty
More Advisor NewsAnnuity News
Health/Employee Benefits News
- Senate passes bill capping medical insurance coverage
- Targeted by Trump, Medicaid funding stirs debate as CT changes rules for hospitals
- Studies from University of Occupational and Environmental Health Provide New Data on COVID-19 (Avoiding the Use of Outpatient Rehabilitation Services Under Long-term Care Insurance During the Covid-19 Pandemic): Coronavirus – COVID-19
- After more than 1,000 layoffs, worries persist about CVS Health's future in Connecticut
- This West Linn house, birthplace of Oregon prepaid health plans, is on National Historic Register
More Health/Employee Benefits NewsLife Insurance News
- Annual financial and audit reports – JPMORGAN CHASE & CO.
- Conning research: Insurers must be flexible in the 2025
- AM Best Places Credit Ratings of Banner Life Insurance Company and William Penn Life Insurance Company of New York Under Review With Developing Implications
- Best's Review Examines Value in Innovation Culture
- Initial Registration Statement for Employee Benefit Plan (Form S-8)
More Life Insurance News