Systems and methods to evaluate application data

• US 8,694,340 B2
• Filed: 02/21/2012
• Issued: 04/08/2014
• Est. Priority Date: 02/22/2011
• Status: Active Grant

• Current Assignee: United Services Automobile Association
• Original Assignee: United Services Automobile Association
• Inventors: Garza, Erika, Brocker, Troy Avon, Ginther, Mark
• Primary Examiner(s): HAMILTON, SARA CHANDLER
• Application Number:
  US13/401,479
• Publication Number:
  US 20120221359A1
• Time in Patent Office: 777 Days
• Field of Search: 705/4, 705/35
• US Class Current: 705/4
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

The present disclosure introduces systems and methods to evaluate application data. A computer system to evaluate application data is described. In one embodiment, a data module may be used to receive application data and validate the application data against at least one secondary data source. A predictive modeling module may be used to model the application data by applying predictive analytics. Further, a confidence level module may be used to calculate a confidence level factor and at least one aggregate degree of confidence level to evaluate an application. Other embodiments are also described.

Claims

1. A computer system for processing and evaluating application data for insurance, comprising:

a memory configured to store instructions;

a processor disposed in communication with said memory, wherein said processor upon execution of the instructions is configured to;

receive application data for an insurance policy regarding an applicant said application data including a plurality of variables and wherein the plurality of variables comprises individual risk and rate variables;

determine which of the risk and rate variables are most relevant to the insurance policy;

assign greater weight to the risk and rate variables most relevant to the insurance policy;

validate the application data against data from at least a secondary data source;

apply predicative analytics wherein said processor configured to apply predictive analytics includes said processor being further configured to;

analyze the application data and the data from said at least a secondary data source, modeling the application data and the data from said at least a secondary data source using the plurality of variables, and extract information from both the application data and the data from the at least a secondary data source to predict future trends and behavior patterns;

determine a degree of confidence factor for each of the plurality of variables used by the model, wherein the degree of confidence factors estimates the reliability of the plurality of variables used by the model;

calculate an aggregate confidence level by aggregating the degree of confidence factor for each of the plurality of variables, wherein the processor configured to calculate an aggregate confidence level includes the processor being further configured to;

weigh the degree of confidence factors for the risk and rate variables in accordance with the greater weight assigned to the risk and rate variables most relevant to the insurance policy;

issue an insurance policy to the applicant when the aggregate confidence level is within a predetermined threshold for the aggregate confidence level; and

indicate that an insurance policy will not issue to the applicant when the aggregate confidence level is outside the predetermined threshold for the aggregate confidence level.

2. A non-transitory computer readable medium comprising instructions, said instructions when executed by a computer, cause the computer to perform a method for processing and evaluating application data for insurance, the method comprising:

receiving application data for an insurance policy regarding an applicant said application data including a plurality of variables and wherein the plurality of variables comprises individual risk and rate variables;

determining which of the risk and rate variables are most relevant to the insurance policy;

assigning greater weight to the risk and rate variables most relevant to the insurance policy;

validating the application data against data from at least a secondary data source;

applying predicative analytics by;

analyzing the application data and the data from said at least a secondary data source, modeling the application data and the data from said at least a secondary data source using the plurality of variables, and extracting information from both the application data and the data from the at least a secondary data source to predict future trends and behavior patterns;

determining a degree of confidence factor for each of the plurality of variables used by the model, wherein the degree of confidence factors estimates the reliability of the plurality of variables used by the model;

calculating an aggregate confidence level by aggregating the degree of confidence factor for each of the plurality of variables wherein said step of calculating an aggregate confidence level further comprises;

weighing the degree of confidence factors for the risk and rate variables in accordance with the greater weight assigned to the risk and rate variables most relevant to the insurance policy;

issuing an insurance policy to the applicant when the aggregate confidence level is within a predetermined threshold for the aggregate confidence level; and

indicating that an insurance policy will not issue to the applicant when the aggregate confidence level is outside the predetermined threshold for the aggregate confidence level.

3. A computer-implemented method for processing and evaluating application data for insurance, the method comprising the steps of:

receiving, by a computer processor, application data for an insurance policy regarding an applicant said application data including a plurality of variables and wherein the plurality of variables comprises individual risk and rate variables;

determining which of the risk and rate variables are most relevant to the insurance policy;

assigning greater weight to the risk and rate variables most relevant to the insurance policy;

validating, by the computer processor, the application data against data from at least a secondary data source;

applying, by the computer processor, predicative analytics by;

analyzing the application data and the data from said at least a secondary data source, modeling the application data and the data from said at least a secondary data source using the plurality of variables, and extracting information from both the application data and the data from the at least a secondary data source to predict future trends and behavior patterns;

determining, by the computer processor, a degree of confidence factor for each of the plurality of variables used by the model wherein the degree of confidence factors estimates the reliability of the plurality of variables used by the model;

calculating, by the computer processor, an aggregate confidence level by aggregating the degree of confidence factor for each of the plurality of variables, wherein said step of calculating an aggregate confidence level further comprises;

weighting the degree of confidence factors for the risk and rate variables in accordance with the greater weight assigned to the risk and rate variables most relevant to the insurance policy;

issuing, by the computer processor, an insurance policy to the applicant when the aggregate confidence level is within a predetermined threshold for the aggregate confidence level; and

indicating, by the computer processor, that an insurance policy will not issue to the applicant when the aggregate confidence level is outside the predetermined threshold for the aggregate confidence level.

4. The method of claim 3, further comprising providing to the applicant a rate quote for the insurance policy.

5. The method of claim 4, further comprising prior to said step of providing to the applicant a rate quote for the insurance policy, determining the threshold for the aggregate confidence level needed to issue the insurance policy to the applicant.

6. The method of claim 3, wherein said step of modeling the application data and the data from said at least one secondary data source using the plurality of variables further comprises:

flagging conflicts in the application data when compared to the data from the at least a secondary data source.

7. The method of claim 3, wherein the data from the at least a secondary data source is historical data specific to the applicant.

8. The method of claim 3, wherein the data from the at least a secondary data source is third-party data.