US-12620034-B2 - Usage estimation systems and methods for risk association adjustments

Abstract

According to some embodiments, a risk relationship data store may contain electronic records, each electronic record representing a risk relationship between an enterprise and a risk relationship provider (e.g., an insurer), and including, for each risk relationship, an electronic record identifier and a set of estimated usage attribute values. A back-end application computer server may receive, from a current usage data source, current usage information for the enterprise (e.g., financial information, utility information, IoT information, etc.). Based on the current usage information, the computer server may infer a likely actual current usage for the enterprise. The computer server may then compare the likely actual current usage with the predicted usage attribute value to determine a risk difference result and adjust a risk relationship parameter based on the risk difference result.

Inventors

• Brandon A. Banks
• Kenneth J. Zygiel

Assignees

• HARTFORD FIRE INSURANCE COMPANY

Dates

Publication Date

20260505

Application Date

20250127

Claims (20)

1. 1 . An estimated usage risk relationship management system implemented via a back-end application computer server, comprising: (a) a risk relationship data store that contains electronic records, each electronic record representing a risk relationship between an enterprise and a risk relationship provider, and including, for each risk relationship, an electronic record identifier and a predicted usage attribute value; (b) a current usage data source associated with the enterprise; (c) the back-end application computer server, coupled to the risk relationship data store and the current usage data source, including: a computer processor, and a computer memory, coupled to the computer processor, storing instructions that, when executed by the computer processor, cause the back-end application computer server to: (i) obtain a public utility bill; (ii) receive, from the current usage data source, current public utility information for the enterprise for a resource, (iii) receive third-party data and historical data for the resource; (iv) based on the current public utility information for the resource, the received third-party data for the resource and the received historical data for the resource, infer, via a trained machine learning model, a likely actual current usage for the enterprise for the resource; (v) compare the likely actual current usage with the predicted usage attribute value to determine a risk difference result; (vi) automatically adjust a risk relationship parameter based on the risk difference result; (vii) re-train the trained machine learning model in response to receipt of the adjusted risk relationship parameter; and (d) a communication port coupled to the back-end application computer server to facilitate a transmission of data to a remote device to support an interactive display, including an indication of the adjusted risk relationship parameter, via a distributed communication network.
2. 2 . The system of claim 1 , wherein the current usage data source is associated with an Application Programing Interface (“API”).
3. 3 . The system of claim 1 , wherein the current usage data source is associated with at least one of: (i) a public utility, (ii) an electric utility, (iii) a water utility, (iv) a transportation service, and (v) a disposal service.
4. 4 . The system of claim 3 , wherein the public utility information is associated with at least one of: (i) an amount of electric power, and (ii) an amount of water.
5. 5 . The system of claim 4 , wherein the current usage data source is associated with at least one of: (i) a physical sensor, and (ii) a usage meter.
6. 6 . The system of claim 1 , wherein optical character recognition (OCR) is applied to the public utility bill.
7. 7 . The system of claim 1 , wherein the risk relationship provider comprises an insurer and the risk relationship is associated with an insurance policy.
8. 8 . The system of claim 7 , wherein the insurance policy is associated with at least one of: (i) business insurance, (ii) general liability insurance, (iii) property insurance, (iv) professional liability insurance, (v) business interruption insurance, and (vi) business liability insurance.
9. 9 . The system of claim 8 , wherein the adjusted risk relationship parameter is associated with at least one of: (i) an insurance premium, (ii) a rate change, (iii) a limits change, (iv) a classification, (v) a coverage, (vi) a deductible amount, (vii) a renewal, (viii) a new type of insurance, and (ix) an endorsement.
10. 10 . The system of claim 1 , wherein the back-end application computer server is associated with at least one of: (i) Machine Learning (“ML”), (ii) Artificial Intelligence (“AI”), and (iii) a predictive model.
11. 11 . A computerized estimated usage risk relationship management method implemented via a back-end application computer server, comprising: accessing, by the back-end application computer server, a risk relationship data store that contains electronic records, each electronic record representing a risk relationship between an enterprise and a risk relationship provider, and including, for each risk relationship, an electronic record identifier and a predicted usage attribute value; obtaining a public utility bill; receiving, from a current usage data source, current public utility information for the enterprise for a resource; receive third-party data and historical data for the resource, based on the current public utility information for the resource, the received third-party data for the resource and the received historical data for the resource, inferring, via a trained machine learning model, a likely actual current usage for the enterprise for the resource; comparing the likely actual current usage with the predicted usage attribute value to determine a risk difference result; automatically adjusting a risk relationship parameter based on the risk difference result; re-training the trained machine learning model in response to receipt of the adjusted risk relationship parameter; and arranging to provide an interactive display, including an indication of the adjusted risk relationship parameter, via a distributed communication network.
12. 12 . The method of claim 11 , wherein the current usage data source is associated with at least one of: (i) a public utility, (ii) an electric utility, (iii) a water utility, (iv) a transportation service, and (v) a disposal service.
13. 13 . The method of claim 12 , wherein the public utility information is associated with at least one of: (i) an amount of electric power, and (ii) an amount of water.
14. 14 . The method of claim 13 , wherein the current usage data source is associated with at least one of: (i) a physical sensor, and (ii) a usage meter.
15. 15 . The method of claim 11 , wherein the current usage data source is associated with an Application Programing Interface (“API”).
16. 16 . The method of claim 11 , wherein optical character recognition (OCR) is applied to the public utility bill.
17. 17 . A non-transitory, computer-readable medium storing instructions, that, when executed by a processor, cause the processor to perform an estimated usage risk relationship management method implemented via a back-end application computer server, the method comprising: accessing, by the back-end application computer server, a risk relationship data store that contains electronic records, each electronic record representing a risk relationship between an enterprise and a risk relationship provider, and including, for each risk relationship, an electronic record identifier and a predicted usage attribute value; obtaining a public utility bill; receiving, from a current usage data source, current public utility information for the enterprise for a resource; receiving third-party data and historical data for the resource; based on the current public utility information for the resource, the received third-party data for the resource and the received historical data for the resource, inferring, via a trained machine learning model, a likely actual current usage for the resource; comparing the likely actual current usage with the predicted usage attribute value to determine a risk difference result; automatically adjusting a risk relationship parameter based on the risk difference result; re-training the trained machine learning model in response to receipt of the adjusted risk relationship parameter; and arranging to provide an interactive display, including an indication of the adjusted risk relationship parameter, via a distributed communication network.
18. 18 . The medium of claim 17 , wherein the risk relationship provider comprises an insurer and the risk relationship is associated with an insurance policy.
19. 19 . The medium of claim 18 , wherein the insurance policy is associated with at least one of: (i) business insurance, (ii) general liability insurance, (iii) property insurance, (iv) professional liability insurance, (v) business interruption insurance, and (vi) business liability insurance.
20. 20 . The medium of claim 19 , wherein the adjusted risk relationship parameter is associated with at least one of: (i) an insurance premium, (ii) a rate change, (iii) a limits change, (iv) a classification, (v) a coverage, (vi) a deductible amount, (vii) a renewal, (viii) a new type of insurance, and (ix) an endorsement.

Description

CROSS-REFERENCE TO RELATED APPLICATION The present application is a continuation of U.S. patent application Ser. No. 18/470,014 entitled “USAGE ESTIMATION SYSTEM AND METHODS FOR RISK ASSOCIATION ADJUSTMENTS” and filed Sep. 19, 2023, which is a continuation of U.S. Pat. No. 11,798,093 (U.S. Publication Ser. No. 17/066,803) entitled “USAGE ESTIMATION SYSTEM AND METHODS FOR RISK ASSOCIATION ADJUSTMENTS” and filed Oct. 9, 2020. The entire contents of these applications are incorporated herein by reference. TECHNICAL FIELD The present application generally relates to computer systems and more particularly to computer systems that are adapted to accurately and/or automatically estimate and/or measure usage information for an enterprise. BACKGROUND An enterprise may enter into a risk relationship with a risk relationship provider (e.g., an insurer) to protect itself from damages associated with unexpected occurrences. For example, the risk relationship may provide payments associated with unforeseen accidents, weather events, work stoppages, etc. Several factors may influence the amount of risk associated with a particular type of risk, such as the size of a building, an amount of product that is manufactured or sold, etc. To help determine this information, an insurer might ask a business “how much product will you sell next year?” and the business might reply “10 million dollars of product,” “1,000 units,” etc. This information may then be used to calculate attributes of an insurance policy (e.g., premium values, exclusions and risk classifications, etc.). In other cases, an insurer might look at previous data associated with the business and assume that next year's numbers will be similar or follow a predicable trend. Such an approach, however, can be a time consuming and unreliable process. For example, an unexpected national or global slowdown might cause the amount of product manufactured and/or sold to suddenly fall. It would be desirable to provide systems and methods to automatically estimate and/or measure usage information in a way that provides fast and accurate results. Moreover, the estimated and measured usage information should be easy to access, understand, update, etc. SUMMARY OF THE INVENTION According to some embodiments, systems, methods, apparatus, computer program code and means are provided to automatically estimate and/or measure usage information in a way that provides fast and accurate results and that allows for flexibility and effectiveness when responding to those results. In some embodiments, a risk relationship data store contains electronic records, each electronic record representing a risk relationship between an enterprise and a risk relationship provider (e.g., an insurer), and including, for each risk relationship, an electronic record identifier and a set of estimated usage attribute values. A back-end application computer server may receive, from a current usage data source, current usage information for the enterprise (e.g., financial information, utility information, IoT information, etc.). Based on the current usage information, the computer server may infer a likely actual current usage for the enterprise. The computer server may then compare the likely actual current usage with the predicted usage attribute value to determine a risk difference result and adjust a risk relationship parameter based on the risk difference result. Some embodiments comprise: means for accessing, by a back-end application computer server, a risk relationship data store that contains electronic records, each electronic record representing a risk relationship between an enterprise and a risk relationship provider, and including, for each risk relationship, an electronic record identifier and a predicted usage attribute value; means for receiving, from a current usage data source, current usage information for the enterprise; based on the current usage information, means for inferring a likely actual current usage for the enterprise; means for comparing the likely actual current usage with the predicted usage attribute value to determine a risk difference result; means for adjusting a risk relationship parameter based on the risk difference result; and means for arranging to provide an interactive display, including an indication of the adjusted risk relationship parameter, via a distributed communication network. In some embodiments, a communication device associated with a back-end application computer server exchanges information with remote devices in connection with an interactive graphical user interface. The information may be exchanged, for example, via public and/or proprietary communication networks. A technical effect of some embodiments of the invention is an improved and computerized way to automatically predict and/or measure usage in a way that provides fast and accurate results. With these and other advantages and features that will become hereinafter apparent, a more complete un