Patent Issued for Prioritization Of Insurance Requotations (USPTO 10,482,536)
2019 DEC 02 (NewsRx) -- By a
The patent’s inventors are Doyle,
This patent was filed on
From the background information supplied by the inventors, news correspondents obtained the following quote: “People seeking insurance coverage (e.g., vehicle insurance, homeowner insurance, life insurance, commercial property insurance, etc.), sometimes request an insurance quotation from two or more different insurance agents and/or insurance agencies associated with different insurance providers. After comparing different competitive insurance quotations, the insurance consumer may decide to purchase insurance coverage from the insurance provider having the price and/or coverage noted in the quotation that best meets his or her needs. Because many of these insurance quotations do not close or otherwise result in an insurance policy, the insurance provider may have a data repository containing a large number of closed (e.g., binding) and/or unclosed (e.g., non-binding) insurance quotations.
“The insurance provider may desire to use these previous insurance consumer contacts as a source of potential insurance leads. The insurance provider may rely on their affiliated insurance agents or agencies to follow up on previously unclosed quotations. Therefore, a uniform process and/or methodology to allow insurance agents or agencies to efficiently manage and pursue multiple insurance re-quotations in a prioritized, optimized manner is desirable.”
Supplementing the background information on this patent, NewsRx reporters also obtained the inventors’ summary information for this patent: “The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosure. The summary is not an extensive overview of the disclosure. It is neither intended to identify key or critical elements of the disclosure nor to delineate the scope of the disclosure. The following summary merely presents some concepts of the disclosure in a simplified form as a prelude to the description below.
“Aspects of the disclosure relate to systems, devices, computer-implemented methods, and computer-readable media for prioritizing an insurance re-quotation process. For example, a computer-assisted method may include receiving, by at least one computing device, a list of insurance leads. The insurance leads may include information about individuals who received a previous quotation for insurance coverage but did not purchase the insurance coverage. The computing device may identify a difference between the previous quotation for insurance coverage and a new quotation for insurance coverage. This identified difference may include at least one of an increase in offered insurance coverage and a reduction in cost. The computing device may then calculate a probability for each of the individuals on the list using a statewide regression model based, at least in part on the identified difference. An output generated by the statewide regression model may correspond to a probability that a resident of a particular state will purchase insurance in response to a re-quotation for insurance coverage. The computing device may then assign a ranking to each of the individuals on the list based on the probability output from the statewide regression model, where the ranking is calculated in relation to other individuals on the list. For example a ranked list may include groupings of insurance quotations, where each grouping given a grade representative of a likelihood that an associated individual will purchase insurance in response to the insurance re-quotation.
“In accordance with additional aspects of the disclosure, various devices and systems may be used to implement a system comprising a data repository and a computing device having a processor and a non-transitory memory device. In some cases, the data repository may store information associated with insurance quotations that did not result in an insurance coverage purchase. The computing device may be communicatively coupled to the data repository, such as to receive a list containing information about unclosed insurance quotations. In some cases, the processor may process instructions stored in the non-transitory memory to cause the computing device to retrieve the list of insurance leads from the data repository, insurance leads comprising individuals who received an insurance quotation but did not purchase insurance coverage in response to the insurance quotation. The computing device may then calculate, using a state regression model, a probability that an individual would purchase insurance coverage after receiving a re-quotation for insurance coverage. Each individual associated with the list may be assigned such a probability. In some cases, the state regression model may include an input comprising a discount not previously offered to the individual. The computing device may associate a ranking to each individual based on the calculated probability. This ranking may correspond to a likelihood that the individual will purchase insurance coverage in response to a re-quotation, where the ranking is determined in relation to the other individuals in the list. The computing device may then communicate, via a network, a ranked list to an insurance agent, a call center and/or insurance agency for use in providing insurance re-quotations to individuals associated with the list. The ranking may be used to determine an order in which to contact the individuals.
“In accordance with additional aspects of the disclosure, a non-transitory computer readable medium may store instructions that, when executed by the processor, cause the processor to retrieve a first list of insurance leads from the data repository. These insurance leads may include individuals associated with a first state that received an insurance quotation, but did not purchase insurance coverage in response to the insurance quotation. in some cases, a second list of insurance leads may be retrieved from the data repository, where the second list comprises individuals associated with a second state that received an insurance quotation, but did not purchase insurance coverage in response to the insurance quotation. The computing device may then calculate, such as by using a first state regression model corresponding to the first state, a probability that each individual associated with the first list of insurance leads would purchase insurance coverage after receiving a re-quotation for insurance coverage. Similarly, the computing device may calculate, using a second state regression model corresponding to the second state, a probability that each individual associated with the second list of insurance leads would purchase insurance coverage after receiving a re-quotation for insurance coverage. Inputs to the first and second state logistic regression models may include a discount not previously offered to the individual. In some cases, the computing device may generate a first ranked list from the first list of insurance leads and a second ranked list from the second list of insurance leads. The first ranked list and the second ranked list may include a plurality of grade classifications that correspond to a subset of individuals associated with the respective lists. Each individual may be assigned a grade classification based on the probability that the individual would purchase insurance when offered a re-quotation for insurance coverage.
“In accordance with additional aspects of the disclosure, an illustrative method may include receiving, by at least one computing device, a list of insurance leads. The insurance leads may include individuals who received a previous quotation for insurance coverage but did not purchase the insurance coverage. The computing device may identify a difference between the previous quotation for insurance coverage and a new quotation for insurance coverage, wherein the difference comprises at least one of an increase in offered insurance coverage and a reduction in cost. The computing device may then calculate a probability for each of the individuals on the list using a national regression model based, at least in part on the identified difference. An output of the national regression model may correspond to the probability that an individual will purchase insurance in response to a re-quotation for insurance coverage. In some cases, an input to the national regression model may include a state of residence of the individual. Once the probabilities are computed for each individual associated with the list, the computing device may assign a ranking to each of the individuals on the list based on the probability output from the national regression model. In some cases, the ranking may be determined in relation to other individuals on the list.
“In accordance with additional aspects of the disclosure, an illustrative system may include a data repository storing information associated with insurance quotations that did not result in an insurance coverage purchase and a computing device communicatively coupled to the data repository, such as via a network. The computing device may include a processor and a non-transitory memory device that may store instructions that, when executed by the processor, cause the computing device to retrieve a list of insurance leads from the data repository. In some cases, the insurance leads may comprise individuals who received an insurance quotation but did not purchase insurance coverage in response to the insurance quotation. The computing device may calculate for each individual associated with the list of insurance leads, a probability that the individual would purchase insurance coverage after receiving a re-quotation for insurance coverage using a nationwide regression model. An input to the national regression model may include a discount not previously offered to the individual. The computing device may assign a ranking to each individual based on the probability and communicate, via the network, a ranked list to an insurance agent for use in providing the re-quotation to the individuals associated with the list. In some cases, the ranking may be used to determine which of the individuals to target in a marketing campaign and/or an order in which each individual is contacted.
“In accordance with additional aspects of the disclosure, an illustrative non-transitory computer readable medium may store instructions that, when executed by a processor, may cause the processor to retrieve a list of insurance leads from the data repository. The data repository may store insurance leads associated with individuals resident in a first state and individuals resident in a second state. In some cases, the individuals may have received an insurance quotation but did not purchase insurance coverage in response to the insurance quotation. The processor may then be caused to calculate, using a nationwide regression model, a probability that each individual associated with the list of insurance leads would purchase insurance coverage after receiving a re-quotation for insurance coverage. An input to the nationwide logistic regression model may include a discount not previously offered to the individual. The processor may then generate a first ranked list associated with the first state based on the list of insurance leads, wherein the first ranked list may include a listing of individuals classified using a plurality of grade classifications. The grade classification may be based on the probability that the individual would purchase insurance when offered a re-quotation for insurance coverage. The processor may also generate a second ranked list associated with the second state based on the list of insurance leads. The second ranked list may include a listing of individuals classified using a plurality of grade classifications. The grade classification may be based on the probability that the individual would purchase insurance when offered a re-quotation for insurance coverage. In some cases, the grade classifications associated with the first state may be different from the grade classifications associated with the second state.
“According to an aspect of the invention, an input corresponding to vehicle insurance coverage associated with one or more state regression model and/or to the national regression model may include one or more of zip code, gender, marital status, driving history, vehicle year, vehicle make, vehicle model, ownership status of real estate, credit worthiness, and length of time with current automobile insurer.
“Other features and advantages of the disclosure will be apparent from the additional description provided herein.”
The claims supplied by the inventors are:
“What is claimed is:
“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.”
For the URL and additional information on this patent, see: Doyle,
(Our reports deliver fact-based news of research and discoveries from around the world.)
APRA Intervenes to Improve Sustainability of Individual Disability Income Insurance
Proposed Collection of Information: Offering of U.S. Mortgage Guaranty Insurance Company Tax and Loss Bonds
Advisor News
Annuity News
Health/Employee Benefits News
Life Insurance News