Prioritization of insurance requotations

• US 10,482,536 B1
• Filed: 07/09/2014
• Issued: 11/19/2019
• Est. Priority Date: 07/09/2014
• Status: Active Grant

• Current Assignee: Allstate Insurance Company (Allstate Corporation)
• Original Assignee: Allstate Insurance Company (Allstate Corporation)
• Inventors: Doyle, Alexander, Dunn, Ryan, Gheorghe, Cristina I., Huls, Eric, Lavigne, Michael A., MacInnis, David, DeCleene, Christopher Joseph
• Primary Examiner(s): Brindley, Benjamin S
• Application Number:
  US14/327,242
• Time in Patent Office: 1,959 Days
• Field of Search: 705 4
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

A computer-assisted method for providing re-quotations for insurance coverage may include receiving a list of insurance leads corresponding to individuals who received a previous quotation for insurance coverage but did not purchase the insurance coverage and identifying a difference between the previous quotation and a new quotation. This difference may include an increase in offered insurance coverage and/or a reduction in cost. A computing device may calculate a probability for each of the individuals on the list using a regression model based, at least in part, on the identified difference. In some cases, the regression model may be associated with individual states. In other cases, the regression model may correspond to a plurality of states. The regression model may output a probability that a resident of a particular state will purchase insurance in response to a re-quotation for insurance coverage, where individuals may then be ranked based on the probability.

Claims

1. A system comprising:

an insurance quotation data repository computing device storing information corresponding to a plurality of historical unclosed insurance quotations that previously did not result in a sale;

one or more computer devices comprising;

a processor; and

a non-transitory memory device storing instructions that, when executed by the processor, cause the one or more computer devices to;

retrieve, from the insurance quotation data repository computing device, information associated with the plurality of historical unclosed insurance quotations, wherein the information retrieved from the insurance quotation data repository computing device includes at least one of a quotation identifier, a name, an address, and a phone number;

generate a list of insurance leads based on information stored on the insurance quotation data repository computing device including a type of insurance coverage to be offered and a geographic location of one or more individuals associated with the historical unclosed insurance quotations, wherein the one or more individuals received one of the historical unclosed insurance quotations but did not purchase insurance coverage;

store, in a lead list data repository, the list of insurance leads, wherein each lead in the list of insurance leads corresponds to an individual associated with at least one of the historical unclosed insurance quotations;

receive the list of insurance leads from the lead list data repository communicatively coupled to the one or more computing devices, wherein the insurance leads correspond to the plurality of historical unclosed insurance quotations;

generate a re-quotation for insurance coverage for each lead included on the list of insurance leads, the re-quotation including a difference from a previously unclosed insurance quotation, wherein the difference comprises at least one of an insurance coverage difference and a cost difference;

generate, based on analyzing the information associated with the plurality of historical insurance unclosed insurance quotations and information associated with the re-quotation, a multi-state regression model, wherein the multi-state regression model is common to a plurality of states;

calculate a likelihood of closing for each of the leads using the multi-state regression model;

determine a ranking for each of the leads based on the likelihood of closing output by the multi-state regression model, wherein the ranking for each of the leads is assigned in relation to other leads on the list of insurance leads; and

communicate, via a network, a first portion of the list of insurance leads to a first remote network device and a second portion of the list of insurance leads to a second device, wherein the first portion of the list of insurance leads includes lead data records associated with a first ranking range and the second portion of the list of insurance leads includes lead data records associated with a second ranking range.

2. The system of claim 1, wherein the non-transitory memory device further stores instructions that, when executed by the processor, cause the one or more computing devices to:

filter the list of insurance leads based on a do-not-call list; and

generate a filtered insurance lead list for evaluation using the multi-state regression model.

3. The system of claim 2, wherein the non-transitory memory device further stores instructions that, when executed by the processor, cause the one or more computing devices to:

filter the list of insurance leads based on public record information, wherein the public record information includes at least one of property transaction information, phone directory information, birth record information, death notice information, and name change information.

4. The system of claim 1, wherein the instructions to generate the list of insurance leads further comprises instructions that, when executed by the processor, cause the one or more computer devices to:

identify one or more previously unclosed insurance quotations that were generated within a specified time period; and

generate the list of insurance leads using the identified one or more previously unclosed insurance quotations that were generated within the specified time period.

5. The system of claim 4, wherein the specified time period is six months.

6. The system of claim 1, wherein the multi-state regression model is generated as a function of two or more input parameters using a logistic regression function and is further based on historical insurance quotation information obtained from the plurality of states, and

wherein the logistic regression function comprises a combination of an intercept parameter and two or more weighting parameters each associated with the two or more input parameters.

7. The system of claim 6, wherein inputs to the multi-state regression model comprise at least two of an insurance premium parameter, an insured items parameter, a discount parameter, a customer credit parameter, an age parameter, a number of insured individuals parameter, and a quotation method parameter.

8. The system of claim 7, wherein an input to the multi-state regression model corresponds to a current insurance policy associated with the individual, wherein the input comprises at least one of an insurance provider parameter and a renewal date parameter associated with the current insurance policy.

9. The system of claim 8, wherein a coefficient associated with the insurance provider parameter or the renewal date parameter corresponds to a time difference between a renewal date and a present date.

10. The system of claim 9, wherein the coefficient nears a maximum value when the time difference between the renewal date and the present date approaches approximately one month.

11. A method comprising:

retrieving, by a processor of a first computing device and from an insurance quotation data repository computing device, information associated with a plurality of historical unclosed insurance quotations that previously did not result in a sale, wherein the information includes at least one of a quotation identifier, a name, an address, and a phone number;

generating, by the processor, a list of insurance leads based on information stored on the insurance quotation data repository computing device including a type of insurance coverage to be offered and a geographic location of one or more individuals associated with the historical unclosed insurance quotations, wherein the one or more individuals received one of the historical unclosed insurance quotations but did not purchase insurance coverage;

storing, by the processor and in a lead list data repository, the list of insurance leads, wherein each lead in the list of insurance leads corresponds to an individual associated with at least one of the historical unclosed insurance quotations;

receiving, by the processor, the list of insurance leads from the lead list data repository communicatively coupled to the one or more computing devices, wherein the insurance leads correspond to the plurality of historical unclosed insurance quotations;

generating, by the processor, a re-quotation for insurance coverage for each lead included on the list of insurance leads, the re-quotation including a difference from a previously unclosed insurance quotation, wherein the difference comprises at least one of an insurance coverage difference and a cost difference;

generating, by the processor and based on analyzing the information associated with the plurality of historical insurance unclosed insurance quotations and information associated with the re-quotation, a multi-state regression model, wherein the multi-state regression model is common to a plurality of states;

calculating, by the processor, a likelihood of closing for each of the leads using the multi-state regression model;

determining, by the processor, a ranking for each of the leads based on the likelihood of closing output by the multi-state regression model, wherein the ranking for each of the leads is assigned in relation to other leads on the list of insurance leads; and

communicating, by the processor and via a network, a first portion of the list of insurance leads to a first remote network device and a second portion of the list of insurance leads to a second device, wherein the first portion of the list of insurance leads includes lead data records associated with a first ranking range and the second portion of the list of insurance leads includes lead data records associated with a second ranking range.

12. The method of claim 11, further comprising:

filtering the list of insurance leads based on a do-not-call list; and

generating a filtered insurance lead list for evaluation using the multi-state regression model.

13. The method of claim 12, further comprising:

filtering the list of insurance leads based on public record information, wherein the public record information includes at least one of property transaction information, phone directory information, birth record information, death notice information, and name change information.

14. The method of claim 11, further comprising:

identifying one or more previously unclosed insurance quotations that were generated within a specified time period; and

generating the list of insurance leads using the identified one or more previously unclosed insurance quotations that were generated within the specified time period.

15. The method of claim 11, wherein the multi-state regression model is generated as a function of two or more input parameters using a logistic regression function and is further based on historical insurance quotation information obtained from the plurality of states, and

wherein the logistic regression function comprises a combination of an intercept parameter and two or more weighting parameters each associated with the two or more input parameters.

16. The method of claim 15, wherein inputs to the multi-state regression model comprise at least two of an insurance premium parameter, an insured items parameter, a discount parameter, a customer credit parameter, an age parameter, a number of insured individuals parameter, and a quotation method parameter.

17. The method of claim 16, wherein an input to the multi-state regression model corresponds to a current insurance policy associated with the individual, wherein the input comprises at least one of a an insurance provider parameter and a renewal date parameter associated with the current insurance policy.

18. The method of claim 17, wherein a coefficient associated with the insurance provider parameter or the renewal date parameter corresponds to a time difference between a renewal date and a present date.

19. The method of claim 18, wherein the coefficient nears a maximum value when the time difference between the renewal date and the present date approaches approximately one month.

20. A non-transitory, computer-readable medium storing instructions that, when executed by a processor, cause the processor to:

retrieve, from an insurance quotation data repository computing device, information associated with the plurality of historical unclosed insurance quotations that previously did not result in a sale, wherein the information includes at least one of a quotation identifier, a name, an address, and a phone number;

generate a list of insurance leads based on information stored on the insurance quotation data repository computing device including a type of insurance coverage to be offered and a geographic location of one or more individuals associated with the historical unclosed insurance quotations, wherein the one or more individuals received one of the historical unclosed insurance quotations but did not purchase insurance coverage;

store, in a lead list data repository, the list of insurance leads, wherein each lead in the list of insurance leads corresponds to an individual associated with at least one of the historical unclosed insurance quotations;

receive the list of insurance leads from the lead list data repository communicatively coupled to the one or more computing devices, wherein the insurance leads correspond to the plurality of historical unclosed insurance quotations;

generate a re-quotation for insurance coverage for each lead included on the list of insurance leads, the re-quotation including a difference from a previously unclosed insurance quotation, wherein the difference comprises at least one of an insurance coverage difference and a cost difference;

generate, based on analyzing the information associated with the plurality of historical insurance unclosed insurance quotations and information associated with the re-quotation, a multi-state regression model, wherein the multi-state regression model is common to a plurality of states;

calculate a likelihood of closing for each of the leads using the multi-state regression model;

determine a ranking for each of the leads based on the likelihood of closing output by the multi-state regression model, wherein the ranking for each of the leads is assigned in relation to other leads on the list of insurance leads; and

communicate, via a network, a first portion of the list of insurance leads to a first remote network device and a second portion of the list of insurance leads to a second device, wherein the first portion of the list of insurance leads includes lead data records associated with a first ranking range and the second portion of the list of insurance leads includes lead data records associated with a second ranking range.