# US 12,602,730 B2 · Machine-learning driven data analysis based on demographics, risk, and need

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,602,730 B2
- Document ID: US12602730B2
- Status: Granted
- Kind: B2
- Application number: 18/776,410
- Filed: 2024-07-18
- Published: 2024-12-05
- Granted: 2026-04-14
- Earliest claimed: 2021-04-13
- Assignees: Nayya Health, Inc.
- Applicants: Nayya Health, Inc.
- Inventors: Sina Chehrazi; Josh Allen Brown; Lisa Renee Carpenter; Akash Magoon; Aman Magoon
- Web page: https://patentgrep.com/patent/US12602730B2

## CPC

- G06Q 40/0822: {by determining insurance risk or fault}
- G06N 20/00: Machine learning
- G06Q 30/0203: Market surveys; Market polls
- G06Q 40/08: Insurance
- G06Q 40/082: {platforms for insurance research, comparison or matching insurance customers and providers using insurance risk factors}
- G06Q 50/00: Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism (healthcare informatics G16H)
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

A data processing system for recommending insurance plans implements obtaining an electronic copy of demographic information associated with a user; analyzing the demographic information with a first machine learning model to recommend a bundle of insurance policies based on the demographic information, wherein the first machine learning model is configured to group insured people having similar demographics into clusters and to generate the bundle of insurance policies based on predicted medical insurance consumption associated with a respective group into which the model predicts that the first user falls; customizing the recommended bundle of insurance policies based on the demographic information associated with the user to generate a customized bundle of insurance policies; generating an insurance recommendation report that presents the customized bundle of insurance policies to the user; and causing a user interface of a display of a computing device associated with the user to present the insurance recommendation report.

## Claims

### Claim 1

A data processing system comprising:
a processor; and
a machine-readable medium storing executable instructions that, when executed, cause the processor to perform operations comprising:
obtaining an electronic copy of first demographic information associated with a user from a plurality of electronic data sources via secure and authenticated pipelines;
analyzing the first demographic information using a parsing engine to reformat the first demographic information according to a standard schema to generate first standardized demographic information;
analyzing the first standardized demographic information to obtain predicted medical spending information for the user by analyzing the first demographic information using a consumption cluster prediction model, the consumption cluster prediction model being trained using training data formatted according to the standard schema to associate the user with a cluster of other people based on the first demographic information and to output predicted medical spending information for the user based on medical spending by the cluster of other people;
providing the predicted medical spending information to a recommendation engine to generate a customized comprehensive insurance plan for the user comprising a plurality of insurance policies based on the predicted medical spending information;
generating an insurance recommendation report that presents the customized comprehensive insurance plan to the user;
causing a user interface of a display of a computing device associated with the user to present the insurance recommendation report;
receiving feedback from a plan recommendation unit based on user acceptance of the customized comprehensive insurance plan;
analyzing the feedback using a model update unit; and
fine-tuning training of the consumption cluster prediction model based on the feedback.

### Claim 2 (depends on 1)

The data processing system of claim 1, wherein the customized comprehensive insurance plan comprises a bundle of insurance policies selected based on the predicted medical spending information.

### Claim 3 (depends on 2)

The data processing system of claim 2, wherein generating the insurance recommendation report further comprises:
obtaining a description of each insurance policy including the bundle of insurance policies;
generating a narrative indicating why each insurance policy including in the bundle of insurance policies has been selected for the user; and
generating the insurance recommendation report to present the narrative and the description of each insurance policy.

### Claim 4 (depends on 2)

The data processing system of claim 2, wherein the machine-readable medium includes instructions configured to cause the processor to perform:
causing a user interface of a display of a computing device associated with the user to present a policy procurement user interface, the policy procurement user interface configured to guide the user through obtaining one or more policies included in the bundle of insurance policies.

### Claim 5 (depends on 2)

The data processing system of claim 2, wherein the predicted medical spending information includes a predicted amount spent on medical claims and types of claims typically filed by people associated with the cluster of other people.

### Claim 6 (depends on 2)

The data processing system of claim 2, wherein the machine-readable medium includes instructions configured to cause the processor to perform:
dynamically generating a plurality of questions to obtain second demographic information for the user by identifying additional demographic information relevant to the user for determining insurance coverage needs of the user using a demographic information model, the demographic information model trained to receive as an input the first demographic information for the user and to predict and output additional information demographic information relevant for determining insurance coverage needs of the user based on the first demographic information.

### Claim 7 (depends on 6)

The data processing system of claim 6, wherein the machine-readable medium includes instructions configured to cause the processor to perform:
obtaining the second demographic information as responses to the plurality of questions; and
combining the second demographic information with the first demographic information before providing the first demographic information as an input to the consumption cluster prediction model.

### Claim 8

A method implemented in a data processing system for recommending insurance plans, the method comprising:
obtaining an electronic copy of first demographic information associated with a user from a plurality of electronic data sources via secure and authenticated pipelines;
analyzing the first demographic information using a parsing engine to reformat the first demographic information according to a standard schema to generate first standardized demographic information;
analyzing the first standardized demographic information to obtain predicted medical spending information for the user by analyzing the first demographic information using a consumption cluster prediction model, the consumption cluster prediction model being trained using training data formatted according to the standard schema to associate the user with a cluster of other people based on the first demographic information and to output predicted medical spending information for the user based on medical spending by the cluster of other people;
providing the predicted medical spending information to a recommendation engine to generate a customized comprehensive insurance plan for the user comprising a plurality of insurance policies based on the predicted medical spending information;
generating an insurance recommendation report that presents the customized comprehensive insurance plan to the user;
causing a user interface of a display of a computing device associated with the user to present the insurance recommendation report;
receiving feedback from a plan recommendation unit based on user acceptance of the customized comprehensive insurance plan;
analyzing the feedback using a model update unit; and
fine-tuning training of the consumption cluster prediction model based on the feedback.

### Claim 9 (depends on 8)

The method of claim 8, wherein the customized comprehensive insurance plan comprises a bundle of insurance policies selected based on the predicted medical spending information.

### Claim 10 (depends on 9)

The method of claim 9, wherein generating the insurance recommendation report further comprises:
obtaining a description of each insurance policy including the bundle of insurance policies;
generating a narrative indicating why each insurance policy including in the bundle of insurance policies has been selected for the user; and
generating the insurance recommendation report to present the narrative and the description of each insurance policy.

### Claim 11 (depends on 9)

The method of claim 9, further comprising:
causing a user interface of a display of a computing device associated with the user to present a policy procurement user interface, the policy procurement user interface configured to guide the user through obtaining one or more policies included in the bundle of insurance policies.

### Claim 12 (depends on 9)

The method of claim 9, wherein the predicted medical spending information including a predicted amount spent on medical claims and types of claims typically filed by people associated with the cluster of other people.

### Claim 13 (depends on 9)

The method of claim 9, further comprising:
dynamically generating a plurality of questions to obtain second demographic information for the user by identifying additional demographic information relevant to the user for determining insurance coverage needs of the user using a demographic information model, the demographic information model trained to receive as an input the first demographic information for the user and to predict and output additional information demographic information relevant for determining insurance coverage needs of the user based on the first demographic information.

### Claim 14 (depends on 13)

The method of claim 13, further comprising:
obtaining the second demographic information as responses to the plurality of questions; and
combining the second demographic information with the first demographic information before providing the first demographic information as an input to the consumption cluster prediction model.

### Claim 15

A machine-readable medium storing instructions that, when executed, cause a processor of a programmable device to perform operations of:
obtaining an electronic copy of first demographic information associated with a user from a plurality of electronic data sources via secure and authenticated pipelines;
analyzing the first demographic information using a parsing engine to reformat the first demographic information according to a standard schema to generate first standardized demographic information;
analyzing the first standardized demographic information to obtain predicted medical spending information for the user by analyzing the first demographic information using a consumption cluster prediction model, the consumption cluster prediction model being trained using training data formatted according to the standard schema to associate the user with a cluster of other people based on the first demographic information and to output predicted medical spending information for the user based on medical spending by the cluster of other people;
providing the predicted medical spending information to a recommendation engine to generate a customized comprehensive insurance plan for the user comprising a plurality of insurance policies based on the predicted medical spending information;
generating an insurance recommendation report that presents the customized comprehensive insurance plan to the user;
causing a user interface of a display of a computing device associated with the user to present the insurance recommendation report;
receiving feedback from a plan recommendation unit based on user acceptance of the customized comprehensive insurance plan;
analyzing the feedback using a model update unit; and
fine-tuning training of the consumption cluster prediction model based on the feedback.

### Claim 16 (depends on 15)

The machine-readable medium of claim 15, wherein the customized comprehensive insurance plan comprises a bundle of insurance policies selected based on the predicted medical spending information.

### Claim 17 (depends on 16)

The machine-readable medium of claim 16, wherein generating the insurance recommendation report further comprises:
obtaining a description of each insurance policy including the bundle of insurance policies;
generating a narrative indicating why each insurance policy including in the bundle of insurance policies has been selected for the user; and
generating the insurance recommendation report to present the narrative and the description of each insurance policy.

### Claim 18 (depends on 16)

The machine-readable medium of claim 16, wherein the machine-readable medium includes instructions configured to cause the processor to perform:
causing a user interface of a display of a computing device associated with the user to present a policy procurement user interface, the policy procurement user interface configured to guide the user through obtaining one or more policies included in the bundle of insurance policies.

### Claim 19 (depends on 15)

The machine-readable medium of claim 15, wherein the predicted medical spending information including a predicted amount spent on medical claims and types of claims typically filed by people associated with the cluster of other people.

### Claim 20 (depends on 15)

The machine-readable medium of claim 15, the machine-readable medium includes instructions configured to cause the processor to perform:
dynamically generating a plurality of questions to obtain second demographic information for the user by identifying additional demographic information relevant to the user for determining insurance coverage needs of the user using a demographic information model, the demographic information model trained to receive as an input the first demographic information for the user and to predict and output additional information demographic information relevant for determining insurance coverage needs of the user based on the first demographic information;
obtaining the second demographic information as responses to the plurality of questions; and
combining the second demographic information with the first demographic information before providing the first demographic information as an input to the consumption cluster prediction model.