DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status
This Office Action is responsive to communications filed on 10 January 2025; Claim(s) 1-34 is/are pending in the application and have been presented for examination.
Continuation
This application is a continuation application of U.S. Application No. 17/357,760 filed 24 June 2021, now U.S. Patent 12,229,690, ("Parent Application"). In accordance with MPEP §609.02(II)(A)(2) and MPEP §2001.06(b) (last paragraph), the Examiner has reviewed and considered the prior art cited in the Parent Application. Also, in accordance with MPEP §2001.06(b) (last paragraph), all documents cited or considered 'of record' in the Parent Application are now considered cited or 'of record' in this application.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b). The USPTO Internet website contains terminal disclaimer forms which may be used.
Please visit www.uspto.gov/patent/patents-forms. The filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/process/file/efs/guidance/eTD-info-I.jsp.
Claims 1-34 are rejected under the judicially created doctrine of obviousness-type double patenting as being unpatentable over claims 1-20 of U.S. Patent No. 12,229,690. The broad claims in the pending application are rejected under obviousness type double patenting over previously patented narrow claims. Although the conflicting claims are not identical, they are not patentably distinct from each other because the claimed invention in the instant application is fully disclosed and is broader than the claimed invention in Patent No. 12,229,690.
See for example:
Instant Claims 19/016,856
Patent No. 12,229,690 (Parent Application)
Claim 1. A computer system for predicting an expected loss for a set of claim transactions received for processing at a server, the computer system comprising: a computer processor; and a non-transitory storage medium having instructions that when executed by the computer processor perform actions comprising: predicting, at a first prediction model, a claim frequency of the set of claim transactions over a given time period, the first prediction model trained using historical frequency data and segment types, each segment type having corresponding subtypes further defining a type of claim; predicting, at a second prediction model, claim severity of the set of claim transactions during the given time period, the second prediction model trained using historical severity data including average loss severity values based on the segment types and the corresponding subtypes; identifying the expected loss for the set of claim transactions over the given time period by applying a product of outputs of the first prediction model and the second prediction model; and, applying the first and the second prediction model, once trained, for predicting an expected loss for subsequent claim transactions associated with the subtypes.
Claim 1. A computer system for predicting an expected loss for a set of claim transactions received for processing at a server,
the computer system comprising: a computer processor; and a non-transitory computer-readable storage medium storage having instructions that when executed by the computer processor perform actions comprising: predicting, at a first machine learning model, a claim frequency of the set of claim transactions over a given time period, the first machine learning model trained using historical frequency data for an average number of claims from a prior time period and training further performed based on a segment type defining a type of claim being submitted, each type of segment having corresponding peril types further defining the type of claim; predicting, at a second machine learning model, claim severity of the set of claim transactions during the given time period, the second machine learning model trained using historical severity data including an average loss severity value of each claim for the prior time period and based on the segment type and the corresponding peril types; determining the expected loss for the set of claim transactions over the given time period by applying a product of prediction of the first machine learning model and the second machine learning model; and, wherein the first and the second machine learning model, once trained for each of the types of segments and thereby trained for different peril types are applied for predicting a subsequent expected loss for subsequent claims associated with any one of the peril types for each segment type of claim.
Claim 2. The computer system of claim 1, the actions further comprising: training the first and the second prediction model separately for each segment type having associated data sources for each of the historical frequency data, and the historical severity data.
Claim 2. The computer system of claim 1, the actions further comprising: training the first and the second machine learning model separately for each segment type selected from: auto insurance segment and residential insurance segment having associated data sources for each of the historical frequency data, and the historical severity data specific to a particular segment type.
Claim 3. The computer system of claim 1, wherein the first and the second prediction model each utilize a machine learning model.
Claim 4. The computer system of claim 3, wherein the machine learning model utilizes a single gradient boosted tree model.
Claim 3. The computer system of claim 1, wherein the first and the second machine learning model each utilize a single gradient boosted tree model.
Claim 5. The computer system of claim 3, wherein the first prediction model applies a regression technique for characterizing distribution of the historical frequency data.
Claim 6. The computer system of claim 5, where in the regression technique is Poisson regression.
Claim 4. The computer system of claim 3, wherein the first machine learning model applies Poisson regression for characterizing distribution of the historical frequency data.
Claim 7. The computer system of claim 3, wherein the second prediction model applies a regression technique for characterizing distribution of the historical severity data.
Claim 8. The computer system of claim 7, where in the regression technique is Gamma regression.
Claim 5. The computer system of claim 4, wherein the second machine learning model applies Gamma regression for characterizing distribution of the historical severity data.
Claim 9. The computer system of claim 3, further comprising collecting location and peril information relating to each of the set of claim transactions wherein the machine learning model is configured to receive claims having different segments, associated with different locations and different perils.
Claim 6. The computer system of claim 3, further comprising collecting location and peril information relating to each of the set of claim transactions wherein the single gradient boosted tree model is configured to receive insurance claims having different types of insurance segments, associated with different locations and different perils.
Claim 10. The computer system of claim 9, the actions further comprising prior to predicting at the first prediction model, aggregating claim transactions relating to each segment type for subsequent input to each prediction model.
Claim 7. The computer system of claim 6, the actions further comprising prior to predicting at the first machine learning model, aggregating claim transactions relating to each segment type for subsequent input to each machine learning model.
Claim 11. The computer system of claim 1, wherein the first prediction model, and the second prediction model once trained are configured to receive a features dataset for each claim in the set of claim transactions, the features dataset comprising at least one of: client data, product data, user data, location data, claim related data, geographic behavior data, user experience data, policy data and account data.
Claim 12. The computer system of claim 11, wherein the product data comprises vehicle data or residential property data, and the user data comprises driver data or owner data.
Claim 13. The computer system of claim 11, wherein the policy data comprises at least one of: types of coverage, types of endorsements, aggregated policy features and discounts.
Claim 8. The computer system of claim 1, wherein the first machine learning model, and the second machine learning model once trained are configured to receive a claim features dataset for each claim in the set of claim transactions, the claim features dataset comprising at least one of: client data, vehicle data, driver data, location data, claim data, claim amount, geographic statistics data per region, user experience data, types of coverage, types of endorsements, and discounts.
Claim 14. The computer system of claim 1, the actions further comprising: aggregating sum of all claims for a particular account to generate a single claim in the set of claim transactions, the aggregating occurs between a time period when a policy change on the particular account.
Claim 9. The computer system of claim 1, the actions further comprising: aggregating sum of all claims for a particular account to generate a single claim in the set of claim transactions, the aggregating occurs between a first and a second time period when a policy change occurs relating to one or more of the claim transactions for the particular account.
17. A non-transitory storage medium comprising instructions executable by a processor, the instructions comprising steps for the processor to: receive a set of input claims having a dataset defining each claim; extract a set of features associated with each input claim derived from the dataset; apply, for each input claim, a prediction model to predict a loss cost based on extracting the set of features and to infer a claim type of the input claim as related to a segment type, wherein applying the prediction model comprises: applying a first prediction model for predicting a claim frequency for each input claim from the set of features; applying a second prediction model for predicting a claim severity for each input claim from the set of features; and applying a product of each predicted one of the claim frequency and the claim severity via a third loss cost model for identifying the loss cost for each input claim from the set of features based on the segment type.
Claim 10. A non-transitory computer-readable storage medium comprising instructions executable by a processor, the instructions comprising steps for the processor to: receive a set of input claims, the set of input claims having an insurance dataset defining each claim; extract a pre-defined set of claim features associated with each input claim derived from the insurance dataset; apply, for each input claim, a machine-learned model to predict a loss cost based on extracting the pre-defined set of claim features and to infer a claim type of the input claim as related to a segment type selected from different types of insurance segments, wherein applying the machine-learned model comprises: applying a first machine learned model for predicting a claim frequency for each input claim from the set of claim features; applying a second machine-learned model for predicting a claim severity for each input claim from the set of claim features; and applying a product of each predicted one of the claim frequency and the claim severity via a third loss cost model for determining the loss cost for each input claim from the set of claim features based on the segment type inferred.
Claim 18. A computer implemented method for predicting an expected loss for a set of claim transactions received for processing at a server, the computer implemented method comprising:(a) predicting, at a first prediction model, a claim frequency of the set of claim transactions over a given time period, the first prediction model trained using historical frequency data for an average number of claims and segment types, each segment type having corresponding subtypes further defining a type of claim;(b) predicting, at a second prediction model, claim severity of the set of claim transactions during the given time period, the second prediction model trained using historical severity data including average loss severity values based on the segment types and the corresponding subtypes;(c) identifying the expected loss for the set of claim transactions over the given time period by applying a product of outputs of the first prediction model and the second prediction model; and, (d) applying the first and the second prediction model, once trained, for predicting an expected loss for subsequent claim transactions associated with any one of the subtypes.
Claim 11. A computer implemented method for predicting an expected loss for a set of claim transactions received for processing at a server, the computer implemented method comprising:(a) predicting, at a first machine learning model, a claim frequency of the set of claim transactions over a given time period, the first machine learning model trained using historical frequency data for an average number of claims from a prior time period and training further performed based on a segment type defining a type of claim being submitted, each type of segment having corresponding peril types further defining the type of claim;(b) predicting, at a second machine learning model, claim severity of the set of claim transactions during the given time period, the second machine learning model trained using historical severity data including an average loss severity value of each claim for the prior time period and based on the segment type and the corresponding peril types; (c) determining the expected loss for the set of claim transactions over the given time period by applying a product of prediction of the first machine learning model and the second machine learning model; and, wherein the first and the second machine learning model, once trained for each of the types of segments and thereby trained for different peril types are applied for predicting a subsequent expected loss for subsequent claims associated with any one of the peril types for each segment type of claim.
19. The computer implemented method of claim 18, further comprising: training the first and the second prediction model separately for each segment type having associated data sources for each of the historical frequency data, and the historical severity data.
12. The computer implemented method of claim 11, further comprising: training the first and the second machine learning model separately for each segment type selected from: auto insurance segment and residential insurance segment having associated data sources for each of the historical frequency data, and the historical severity data specific to a particular segment type.
20. The computer implemented method of claim 18, wherein: the first and the second prediction model each utilize a machine learning model.
21. The computer implemented method of claim 20, wherein the machine learning model is a single gradient boosted tree model.
13. The computer implemented method of claim 11, wherein: the first and the second machine learning model each utilize a single gradient boosted tree model.
22. The computer implemented method of claim 20, wherein: the first prediction model applies a regression technique for characterizing distribution of the historical frequency data.
23. The computer implemented method of claim 22, wherein the regression technique is Poisson regression.
14. The computer implemented method of claim 13, wherein: the first machine learning model applies Poisson regression for characterizing distribution of the historical frequency data.
24. The computer implemented method of claim 20, wherein: the second prediction model applies a regression technique for characterizing distribution of the historical severity data.
25. The computer implemented method of claim 24, wherein the regression technique is Gamma regression.
15. The computer implemented method of claim 14, wherein: the second machine learning model applies Gamma regression for characterizing distribution of the historical severity data.
26. The computer implemented method of claim 20, further comprising: collecting location and peril information relating to each of the set of claim transactions wherein the machine learning model is configured to receive claims having different segments, associated with different locations and different perils.
16. The computer implemented method of claim 13, further comprising: collecting location and peril information relating to each of the set of claim transactions wherein the single gradient boosted tree model is configured to receive insurance claims having different types of insurance segments, associated with different locations and different perils.
27. The computer implemented method of claim 26, further comprising: prior to predicting at the first prediction model, aggregating claim transactions relating to each segment type for subsequent input to each prediction model.
17. The computer implemented method of claim 16, further comprising: prior to predicting at the first machine learning model, aggregating claim transactions relating to each segment type for subsequent input to each machine learning model.
28. The computer implemented method of claim 20, wherein: the first prediction model, and the second prediction model once trained are configured to receive a features dataset for each claim in the set of claim transactions, the features dataset comprising at least one of: client data, product data, user data, location data, claim related data, geographic behavior data per region, user experience data, policy data, and account data.
29. The computer implemented method of claim 28, wherein the product data comprises vehicle data or residential property data, and the user data comprises driver data or owner data.
30. The computer implemented method of claim 28, wherein the policy data comprises at least one of: types of coverage, types of endorsements, aggregated policy features and discounts.
18. The computer implemented method of claim 11, wherein: the first machine learning model, and the second machine learning model once trained are configured to receive a claim features dataset for each claim in the set of claim transactions, the claim features dataset comprising at least one of: client data, vehicle data, driver data, location data, claim data, claim amount, geographic statistics data per region, user experience data, types of coverage, types of endorsements, and discounts.
31. The computer implemented method of claim 20, further comprising: aggregating sum of all claims for a particular account to generate a single claim in the set of claim transactions, the aggregating occurs between a time period when a policy change occurs on the particular account.
19. (Original) The computer implemented method of claim 11, further comprising: aggregating sum of all claims for a particular account to generate a single claim in the set of claim transactions, the aggregating occurs between a first and a second time period when a policy change occurs relating to one or more of the claim transactions for the particular account.
34. A computer program product comprising a non-transitory storage device storing instructions that when executed by at least one processor of a computing device predict an expected loss for a set of claim transactions received for processing at a server, and configure the computing device to:(a) predict, at a first prediction model, a claim frequency of the set of claim transactions over a given time period, the first prediction model trained using historical frequency data and segment types, each segment type having corresponding subtypes further defining a type of claim;(b) predict, at a second prediction model, claim severity of the set of claim transactions during the given time period, the second prediction model trained using historical severity data including average loss severity values based on the segment types and the corresponding subtypes;(c) identify the expected loss for the set of claim transactions over the given time period by applying a product of outputs of the first prediction model and the second prediction model; and, (d) wherein the first and the second prediction model, once trained for each of the types of segments and thereby trained for different peril types are applying the first and the second prediction model, once trained, to predict a expected loss for subsequent claim transactions associated with any one of the subtypes.
20. A computer program product comprising a non-transitory storage device storing instructions that when executed by at least one processor of a computing device predict an expected loss for a set of claim transactions received for processing at a server, and configure the computing device to:(a) predict, at a first machine learning model, a claim frequency of the set of claim transactions over a given time period, the first machine learning model trained using historical frequency data for an average number of claims from a prior time period and training further performed based on a segment type defining a type of claim being submitted, each type of segment having corresponding peril types further defining the type of claim;(b) predict, at a second machine learning model, claim severity of the set of claim transactions during the given time period, the second machine learning model trained using historical severity data including an average loss severity value of each claim for the prior time period and based on the segment type and the corresponding peril types; (c) determine the expected loss for the set of claim transactions over the given time period by applying a product of prediction of the first machine learning model and the second machine learning model; and, wherein the first and the second machine learning model, once trained for each of the types of segments and thereby trained for different peril types are applied to predict a subsequent expected loss for subsequent claims associated with any one of the peril types for each segment type of claim.
The Applicant is now attempting to claim broadly that which had been previously described in more detail in the claim(s) of Patent No. 12,229,690. Independent claim(s) 17-18 and 34 of the instant application is analyzed similarly, and found to be unpatentable over independent claim(s) 10-11 and 20 of the Parent Application for the same reasons. The differences between the claim(s) appears to be either minor, necessarily required and/or a difference in verbiage to convey the same basic activity. For example at paragraph 0049 of the instant application claim subtypes encompasses insurance perils (0049, “claim subtypes (e.g. insurance perils)” see also 0050), and according to paragraph 0040, insurance segment type encompasses auto and residential insurance (0040, “an estimate of the loss cost related to each segment type (e.g. automobile insurance claims, and home insurance claims)”).
Dependent claims 2-16 and 19-33 of the instant application appear to encompass the same limitations as dependent claims 2-9, 12-19 of Patent No. 12,229,690, and the differences between the claim(s) appears to be either minor, necessarily required and/or a difference in verbiage to convey the same basic activity.
Therefore, 1-34 of the instant claims are found to be double patenting based on the nonstatutory double patenting analysis.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim(s) 1-34 is/are rejected under 35 USC 101 because the claimed invention is directed to an abstract idea without significantly more.
Under Eligibility Step 1 analysis, it is determined that claims 1-34 are directed to a system and method.
Under Eligibility Step 2A, Prong 1 analysis, Claim 1 recites, "A computer system for predicting an expected loss for a set of claim transactions received for processing at a server, the computer system comprising: a computer processor; and a non-transitory storage medium having instructions that when executed by the computer processor perform actions comprising: predicting, at a first prediction model, a claim frequency of the set of claim transactions over a given time period, the first prediction model trained using historical frequency data and segment types, each segment type having corresponding subtypes further defining a type of claim; predicting, at a second prediction model, claim severity of the set of claim transactions during the given time period, the second prediction model trained using historical severity data including average loss severity values based on the segment types and the corresponding subtypes; identifying the expected loss for the set of claim transactions over the given time period by applying a product of outputs of the first prediction model and the second prediction model; and, applying the first and the second prediction model, once trained, for predicting an expected loss for subsequent claim transactions associated with the subtypes”, the underlined limitations indicate additional elements that are to be further analyzed at Step 2A-2. Independent Claim(s) 17-18 and 34 are similar to Claim 1 except for reciting, A non-transitory storage medium comprising instructions executable by a processor, the instructions comprising steps for the processor, applying a product of each predicted one of the claim frequency and the claim severity via a third loss cost model for identifying the loss cost for each input claim from the set of features based on the segment type (Claim 17), A computer implemented method for predicting an expected loss for a set of claim transactions received for processing at a server, the computer implemented method (Claim 18), A computer program product comprising a non-transitory storage device storing instructions that when executed by at least one processor of a computing device (Claim 34), therefore Claims 17-18 and 34 are analyzed similarly as Claim 1.
The Claim(s) are found to be within the enumerated group(s) of Certain Methods of Organizing Human Activity, specifically as it relates to fundamental economic principles or practices specifically as it relates to insurance and mitigating risk. The Claims also appear to recite mathematical concepts as well.
For example, the limitations of predicting a claim frequency of the set of claim transactions over a given time period, using historical frequency data and segment types, predicting claim severity of the set of claim transactions during the given time period using historical severity data including average loss severity values based on the segment types and the corresponding subtypes, identifying the expected loss for the set of claim transactions over the given time period by applying a product of outputs – recite the abstract idea of predicting financial loss as it relates to insurance which is a common business practice. The Examiner finds that the limitations of “applying a product of outputs” recites mathematical concepts (i.e., calculating the predicted loss by applying a product of the two models (frequency x severity)).
Although the Examiner has provided this summary of the Claims, the analysis regarding subject matter eligibility considers the entirety of the claim elements, both individually and as a whole (or ordered combination).
Under Eligibility Step 2A, Prong 2 analysis, the limitations of - A computer system, a server, a computer processor; and a non-transitory storage medium having instructions that when executed by the computer processor (Claim 1), A non-transitory storage medium comprising instructions executable by a processor, the instructions comprising steps for the processor, applying a product of each predicted one of the claim frequency and the claim severity via a third loss cost model for identifying the loss cost for each input claim from the set of features based on the segment type (Claim 17), A computer implemented method for predicting an expected loss for a set of claim transactions received for processing at a server, the computer implemented method (Claim 18), A computer program product comprising a non-transitory storage device storing instructions that when executed by at least one processor of a computing device (Claim 34), wherein the product data comprises vehicle data or residential property data, and the user data comprises driver data or owner data (Claim 9) - does not integrate the judicial exception into practical application because the claims recite generic computer components performing generic computer functions which amounts to nothing more than mere instructions to implement the abstract idea in a computer environment.
Independent Claim(s) 1, 17-18, and 34, recites predicting and applying a first and second prediction model for determining an expected loss the Examiner finds that the prediction model(s) are recited at a high level of generality such that they are merely invoked to perform the abstract idea. Dependent Claim(s) 2-7, 11, 16, 19-25, 28 and 33 recite various limitations regarding training and using the prediction model(s)/machine learning model and are therefore analyzed similarly.
Dependent Claims 11-13 and 28-30 are also considered to be encompassed by the abstract idea for indicating, the type of feature dataset (Claim 11, 28), the type of product data (Claim 12, 29), and the type of policy data (Claim 13, 30).
The limitations of the claim(s) does not appear to recite an improvement to another technology or technical field; does not provide any improvements to the functioning of the computer itself; does not apply the judicial exception with, or by use of, a particular machine; does not effect a transformation or reduction of a particular article to a different state or thing; it does not add a specific limitation, or add unconventional steps that confine the claim(s) to a particular useful application; or other meaningful limitations beyond generally linking the use of the judicial exception to a particular technological environment. Generic computer components performing generic computer functions, without an inventive concept, do not amount to significantly more than the abstract idea. The type of information being manipulated does not impose meaningful limitations or render the idea less abstract. None of the limitations, considered alone or in an ordered combination provide eligibility, because taken as a whole, the claim(s) is/are merely instructions to implement the abstract idea in a computer environment.
Under Eligibility Step 2B analysis, the claim(s) does not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional claim elements, considered individually and as an ordered combination, do not amount to significantly more than the abstract idea. The claim includes that, as stated above, it is implemented by a computer which employs a computer processor is nothing more than “apply it” with instruction to a generic computer. The claimed computer components are recited at a high level of generality and are merely invoked to perform the abstract idea.
Allowable Subject Matter
Claim 1-34 are allowable over the prior art..
The following is a statement of reasons for the indication of allowable subject matter:
The Claim 1 recites, “A computer system for predicting an expected loss for a set of claim transactions received for processing at a server, the computer system comprising: a computer processor; and a non-transitory storage medium having instructions that when executed by the computer processor perform actions comprising: predicting, at a first prediction model, a claim frequency of the set of claim transactions over a given time period, the first prediction model trained using historical frequency data and segment types, each segment type having corresponding subtypes further defining a type of claim; predicting, at a second prediction model, claim severity of the set of claim transactions during the given time period, the second prediction model trained using historical severity data including average loss severity values based on the segment types and the corresponding subtypes; identifying the expected loss for the set of claim transactions over the given time period by applying a product of outputs of the first prediction model and the second prediction model; and, applying the first and the second prediction model, once trained, for predicting an expected loss for subsequent claim transactions associated with the subtypes”, independent Claim(s) 17-18 and 34 are similar and are analyzed similarly as Claim 1.
The closest prior art of record, Wu et al, discloses a system and method for determining severity and frequency of claims using separate models, however Wu does not disclose determining the expected loss for the set of claim transactions over the given time period by applying a product of prediction of the first prediction model and second prediction model.
Hayward et al teaches using machine learning to analyze various insurance claims (including different segments and perils) to identify emerging trends in insurance data. Zizzamia et al teaches estimating insurance loss reserves using traditional GLM model(s). However, neither Hayward or Zizzamia disclose the claim limitations indicated above. Andrist, Binns, Bersano, and/or Peak (see pertinent art cited to but not relied upon below) indicate using traditional predictive modeling to analyze historical claim(s) data to either predict future loss or risk, however none of the above mentioned references disclose the limitation(s) of, “applying a product of outputs of the first prediction model and the second prediction model; and, applying the first and the second prediction model, once trained, for predicting an expected loss for subsequent claim transactions associated with the subtypes”.
The Examiner has searched for but does not find art that discloses, applying a product of outputs of the first prediction model and the second prediction model; and, applying the first and the second prediction model, once trained, for predicting an expected loss for subsequent claim transactions associated with the subtypes - therefore the Examiner has indicated allowability over the prior art.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Andrist et al (U.S. Patent Publication No. 20100063851), indicates rating and pricing insurance policies including a territory factor, the system analyzes historical loss data, geographical data and demographics data, the historical loss data is analyzed to identify a frequency and severity of historical loss by coverage type (see at least Abstract, 0038).
Bersano et al (Japanese Publication No. 2020190983), indicates training a neural network to estimate an unknown total loss based on claim data for which payment of insurance money is not completed, the system further estimates the reserve for outstanding claims needed in the future (see at least Abstract).
Binns et al (U.S. Patent No. 7,392,201), indicates an insurance claim forecasting system that uses person-level enrollment data, historical healthcare claims and historical claim amount as input for a forecasting model to predict future claims (see at least Abstract).
Hayward et al (U.S. Patent Publication No. 20210287297), indicates training and using a machine learning model to predict loss reserves by analyzing historical claim(s) data labeled with a claim loss amount (see at least Abstract, 0076, 0118).
Peak et al (U.S. Patent Publication No. 20110161116), indicates calculating an insurance loss risk score for multiple geographical locations based on historical loss data including average severity and frequency (see at least Abstract, 0042).
Pednault et al (U.S. Patent No. 7,072,841), indicates using predictive modeling to analyze historical insurance data for purposes of determining future insurance rates (see at least Abstract, Summary).
Prendergast et al (U.S. Patent Publication No. 20080126139), indicates determining a rate of insurance for executives of organizations, while taking into account different risk factors (see at least Abstract, Summary).
Kevin Kuo, Ronald Richman. Embedding and attention in predictive modeling, April 9, 2021, accessed at https://arxiv.org/pdf/2104.03545 (Year:2021), discusses how categorical data can be processed with embeddings in the context of claim severity modelling, see at least Abstract.
Gabrielli, Andrea. 2019. “A Neural Network Boosted Double Over-Dispersed Poisson Claims Reserving Model.” SSRN Electronic Journal, April. https://doi.org/10.2139/ssrn.3365517, discusses an actuarial loss reserving technique that takes into account both claim counts and claim amounts, where separate (over-dispersed) Poisson models for the claim counts and the claim amounts are combined by a joint embedding into a neural network architecture (see at least Abstract).
Su X, Bai M. Stochastic gradient boosting frequency-severity model of insurance claims. PLoS One. 2020 Aug 31, discusses developing a data-driven dependent frequency-severity model using a stochastic gradient boosting algorithm to estimate parameters for both claim frequency and severity (see at least Abstract).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MELINDA GIERINGER whose telephone number is (408)918-7593. The examiner can normally be reached Monday - Friday (11AM-6PM ET).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Ilana Spar can be reached on (571)270-7537. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/M.G./Examiner, Art Unit 3622
/ILANA L SPAR/Supervisory Patent Examiner, Art Unit 3622
Prosecution Insights