DETAILED ACTION
Acknowledgements
This office action is in response to the claims filed 03/09/2026.
Claims 1, and 16 are amended.
Claims 2, 5, 6, 9-15, 17 and 20 are cancelled.
Claims 1, 3, 4, 7, 8, 16, 18 and 19 are pending.
Claims 1, 3, 4, 7, 8, 16, 18 and 19 have been examined.
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 .
Response to Arguments
Applicant's arguments filed 03/09/2026 have been fully considered but they are not persuasive.
101
Applicant argues “For example, the claims recite processor-executed operations that dynamically adjust fraud rules in real-time based on catastrophic event detection and reduce false transaction declines in the context of catastrophic events, a significant improvement over traditional payment transaction computerized systems. For example, there is no need for human intervention to reduce the false transactions or process or validate claims (as required in the primary reference cited by the Examiner (See Allerkamp, Office Action, pg. 15 "prompt[s] the client to contact a service representative to further process or validate the claim"). Utilization of the claimed invention prevents a payment system from having to perform computer operations to rehash a payment transaction that has been, for example, falsely declined during a catastrophic event…. As stated previously, the claims significantly improve payment computer systems as there is no need for human intervention to reduce the false transactions or process or validate claims (as required in the primary reference cited by the Examiner (See Allerkamp, Office Action, pg. 15 "prompt[s] the client to contact a service representative to further process or validate the claim").” Examiner disagrees.
First, the argument conflates the 101 subject matter with the 103 prior art rejection. It is unclear how the prior art of Allerkamp, used in the 103 rejection, affects the 101 subject matter rejection of Applicant’s claims.
According to the disclosure(¶ 69), “adjusting fraud rule 391 to include the catastrophic event threshold 371, the catastrophic-event-related-merchant category code 373, and the catastrophic event location 372, improves upon existing fraud detection systems by allowing issuers to suppress fraud decline decisions for certain catastrophic-event-related-merchant category codes during catastrophic events, thereby alleviating painful false declines for certain catastrophic-event-related-merchant category codes.” The recited “practical application”/improvement is not actually performed by a computing device or the recited processor. Rather remote entities “issuers” are the ones that provide Applicants recited improvements. The processor itself does not achieve the recited improvement.
Secondly, the claims recite “training the catastrophic event detection machine learning model to recognize a catastrophic event by assessing the historical catastrophic event data” According to the disclosure(¶ 52-54), “In some embodiments, catastrophic event detector 330 receives the catastrophic event data 360 and payment transaction data 390 and uses a machine learning training application to train a machine learning algorithm to output the catastrophic event detection machine learning model 331. In some embodiments, the catastrophic event detection machine learning model 331 output by the machine learning training application is trained to generate the catastrophic event score 370.” The disclosure does not provide further information on what it means to “train” the model, just that the model is trained with the extracted data. From this “training” could be the sending of extracted information, which falls under the abstract idea or it could be an evaluation that can be done by a human mind, now automated which is itself an abstract idea. Therefore, given the lack of information about the “training”, the training process appears itself to be abstract and not an additional element that would integrate the judicial exception into a practical application
Therefore, based on case law precedent, the claims are claiming subject matter similar to concepts already identified by the courts as dealing with abstract ideas. See Alice Corp. Pty. Ltd., 573 U.S. 208 (citing Bilski v. Kappos, 561, U.S. 593, 611 (2010)). Mere instructions to apply the exception using generic computer components and limitations to a particular field of use or technological environment do not amount to practical applications. The subject matter rejection is retained.
112
Applicant’s arguments and amendments do not address claim 1 nor the lack of written description for “to generate a catastrophic-event-based fraud rule” or that the disclosure makes no mention of “configuring” a fraud rule and how one can be “configured”. The rejections are maintained.
103
Note: Independent claims 1 and 16 recite two different potential inventions. One that performs machine learning training and “configures” a fraud rule and the other that uses machine learning training to train a machine learning model and adjusts a fraud rule. The claims are subject to restriction.
Applicant argues “However, nowhere in Allerkamp, including the paragraph recited by the Examiner, does Allerkamp disclose that a financial rules is adjusted to ascertain a catastrophic-event-based financial fraud rule as recited in amended claim 16 "adjust a financial fraud rule to ascertain the catastrophic-event-based fraud rule, the catastrophic-event-based fraud rule being ascertained by adding a catastrophic event threshold to the financial fraud rule" Allerkamp merely describes performing a comparison to a threshold, which no person of ordinary skill would conclude yields the recited amended claims.” Examiner disagrees.
Allerkamp discloses adjust a financial fraud rule to ascertain the catastrophic-event-based fraud rule, the catastrophic-event-based fraud rule being ascertained by adding a catastrophic event threshold to the financial fraud rule (Abstract; column 11, line 9-67, column 12, line 1-21, column 13, line 1-67, column 14, line 1-7).
According to Applicant’s disclosure(
¶
56), “ In some embodiments, the catastrophic event threshold 371 is a threshold used to determine whether to decline or approve a payment transaction based on the catastrophic event score 370.”
Allerkamp discloses If the threshold risk number is not exceeded, at block 66, the insurance computing system 12 determines that the submitted claim is not fraudulent (e.g., likely not fraudulent) and proceeds to validate the submitted claim, and may eventually make a payout to the client…. The insurance computing system may compare the risk score with a threshold number, and if the threshold number is exceeded, the insurance computing system may prompt the client to contact a service representative to further process or validate the claim. Otherwise, if the threshold number is not exceeded, the insurance computing system may continue processing the claim autonomously…. If the validation process is completed, then the client would eventually receive funds associated with the submitted claim. (Abstract; column 13, line 1-67).
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.
Claims 1, 3, 4, 7, 8, 16, 18 and 19 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Subject Matter Eligibility Standard
When considering subject matter eligibility under 35 U.S.C. § 101, it must be determined whether the claim is directed to one of the four statutory categories of invention, i.e., process, machine, manufacture, or composition of matter (101 Analysis: Step 1). Even if the claim does fall within one of the statutory categories, it must then be determined whether the claim is directed to a judicial exception (i.e., law of nature, natural phenomenon, and abstract idea) (101 Analysis: Step 2a(Prong 1), and if so, Identify whether there are any additional elements recited in the claim beyond the judicial exception(s), and evaluate those additional elements to determine whether they integrate the exception into a practical application of the exception. (101 Analysis: Step 2a (Prong 2). If additional elements does not integrate the exception into a practical application of the exception, claim still requires an evaluation of whether the claim recites additional elements that amount to an inventive concept (aka “significantly more”) than the recited judicial exception. If the claim as a whole amounts to significantly more than the exception itself (there is an inventive concept in the claim), the claim is eligible. If the claim as a whole does not amount to significantly more (there is no inventive concept in the claim), the claim is ineligible. (101 Analysis: Step 2b).
The 2019 PEG explains that the abstract idea exception includes the following groupings of subject matter: a) Mathematical concepts b) Certain methods of organizing human activity and c) Mental processes
Analysis
In the instant case, claim 1 is directed to a method, claims 9 and 16 are directed to an article of manufacture.
101 Analysis: Step 2a (Prong 1) – Identifying an Abstract Idea
The claims recite the steps of “extracting… data… translating data… selecting… model… performing…training… /utilizing … training to train….model … utilizing … model… configuring … rule…/ adjusting … rule… and approving… transaction… .” The claim recites an abstract idea that is directed towards certain methods of organizing human activity, in this case, mitigating risk, specifically, evaluating data to determine fraud for approving a transaction, for example insurance fraud.
101 Analysis: Step 2a (Prong 2) – Identifying a Practical Application
The claim does currently recite a potential additional element but based on the specification, proves to not be an additional element and much more does not integrate the judicial exception into a practical application.
The claim recites “extracting… data from a network.” According to the disclosure(¶ 48), “the historical catastrophic event data 311 and the historical catastrophic event data 312 include historical data related to catastrophic events that have occurred previously and that have been extracted from at least one of a social media resource 361 (such as, for example, social media applications) or news resource 362 (such as, for example, news media applications).” The recited “extraction” is information collected from the news and social media networks, which does not require a computing device.
Secondly, the claims recite “training the catastrophic event detection machine learning model to recognize a catastrophic event by assessing the historical catastrophic event data” According to the disclosure(¶ 52-54), “In some embodiments, catastrophic event detector 330 receives the catastrophic event data 360 and payment transaction data 390 and uses a machine learning training application to train a machine learning algorithm to output the catastrophic event detection machine learning model 331. In some embodiments, the catastrophic event detection machine learning model 331 output by the machine learning training application is trained to generate the catastrophic event score 370.” The disclosure does not provide further information on what it means to “train” the model, just that the model is trained with the extracted data. From this, “training” could be the sending of extracted information, which falls under the abstract idea or it could be an evaluation that can be done by a human mind, now automated which is itself an abstract idea. Therefore, given the lack of information about the “training”, the training process appears itself to be abstract and not an additional element that would integrate the judicial exception into a practical application
Therefore, based on case law precedent, the claims are claiming subject matter similar to concepts already identified by the courts as dealing with abstract ideas. See Alice Corp. Pty. Ltd., 573 U.S. 208 (citing Bilski v. Kappos, 561, U.S. 593, 611 (2010)). Mere instructions to apply the exception using generic computer components and limitations to a particular field of use or technological environment do not amount to practical applications.
101 Analysis - Step 2b
Viewed as a whole, instructions/method claims recite mitigating risk as performed by a generic computer.
Dependent claims 3, 4, 7, 8, 18 and 19 provide further descriptive details of the main crux of the independent claims towards determining whether a transaction is fraudulent.
The method claims do not, for example, purport to improve the functioning of the computer itself. Nor do they effect an improvement in any other technology or technical field. Instead, the claims at issue amount to nothing significantly more than an instruction to apply the abstract idea using some unspecified, generic computer. See Alice Corp. Pty. Ltd., 573 U.S. 208. Mere instructions to apply the exception using a generic computer component and limitations to a particular field of use or technological environment cannot integrate a judicial exception into a practical application at Step 2A or provide an inventive concept in Step 2B. The use of a computer or processor to merely automate and/or implement the abstract idea cannot provide significantly more than the abstract idea itself (MPEP 2106.05(I)(A)(f) & (h)). Therefore, the claim is not patent eligible.
Conclusion
The claim as a whole, does not amount to significantly more than the abstract idea itself. This is because the claim does not affect an improvement to another technology or technical filed; the claim does not amount to an improvement to the functioning of a computer system itself; and the claim does not move beyond a general link of the use of an abstract idea to a particular technological environment.
Accordingly, the Examiner concludes that there are no meaningful limitations in the claim that transform the judicial exception into a patent eligible application such that the claim amounts to significantly more than the judicial exception itself.
Dependent claims do not resolve the deficiency of independent claims and accordingly stand rejected under 35 USC 101 based on the same rationale.
Dependent claims 3, 4, 7, 8, 18 and 19 are also rejected.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1, 3, 4, 7, 8, 16, 18 and 19 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Claims 1, and 16 recite “utilizing the catastrophic event detection machine learning model to generate a catastrophic event score, the catastrophic event score being configured to serve as an indicator of the catastrophic event that is used to determine whether to generate a catastrophic-event-based fraud rule… configuring, at the processor, a financial fraud rule by adjusting the financial fraud rule to yield the catastrophic-event-based fraud rule, the catastrophic -based fraud rule being yielded by adding a catastrophic event threshold to the financial fraud rule.” According to the disclosure(¶ 46, 52, 56, 69, 76-78), “ adjusting fraud rule 391 to include the catastrophic event threshold 371, the catastrophic-event-related-merchant category code 373, and the catastrophic event location 372, improves upon existing fraud detection systems by allowing issuers to suppress fraud decline decisions for certain catastrophic-event-related-merchant category codes during catastrophic events, thereby alleviating painful false declines for certain catastrophic-event-related-merchant category codes.” The disclosure recites “adjusting fraud rule 391 to include the catastrophic event threshold 371, the catastrophic-event-related-merchant category code 373, and the catastrophic event location improves upon existing fraud detection systems by allowing issuers to suppress fraud decline decisions”. The disclosure does not provide support to generate “a catastrophic-event-based fraud rule” or “configuring, at the processor, a financial fraud rule by adjusting the financial fraud rule to yield the catastrophic-event-based fraud rule, the catastrophic -based fraud rule being yielded by adding a catastrophic event threshold to the financial fraud rule”. The disclosure does not provide written description support for the recited limitations. Dependent claims 3, 4, 7, 8, 18 and 19 are also rejected.
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1, 3, 4, 7, and 8 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor, or for pre-AIA the applicant regards as the invention.
Claim 1, recites “configuring, at the processor, a financial fraud rule by adjusting the financial fraud rule to yield the catastrophic-event-based fraud rule, the catastrophic -based fraud rule being yielded by adding a catastrophic event threshold to the financial fraud rule.” The claim is unclear and indefinite. The claim is unclear what computing function a processor performs when directed in “configuring, at the processor, a financial fraud rule to reduce false declines….” There does not appear to be a computing function, rather the recitation of a result. The claims are unclear and indefinite. Dependent claims 3, 4, 7, and 8 are also rejected.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 3, 4, 16, 18 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Allerkamp et al. (US 11,836,803) (“Allerkamp”), and further in view of Elewitz et al. (US 2021/0110294)(“Elewitz”).
Regarding claim 1, Allerkamp discloses extracting, at a processor, historical catastrophic event data from a network (Figure 1; column 8, line 14-66, column 9, line 1-67, column 10, line 1-67; claim 1, 6);
Allerkamp - At block 54, the insurance computing system 12 identifies similar insurance claims associated with the geographical area. In particular, the insurance computing system 12 may send a query to the insurance database 14 for a subset of the claims 22 that were submitted in the same geographical area. (Figure 1; column 8, line 14-66);
translating, at the processor, the historical catastrophic event data into machine learning feature form ( column 8, line 14-66, column 9, line 1-67, column 10, line 1-67; claim 8, 9);
Allerkamp - the insurance computing system 12 may use machine learning algorithms to determine the fraud indicators. That is, the insurance computing system 12 may generate or receive a mathematical model by receiving sample data (e.g., insurance claims that have been identified as fraudulent and insurance claims that have been identified as not fraudulent), predicting whether an insurance claim of the sample data is fraudulent, and receiving an indication of whether the prediction was true or false. The insurance computing system 12 may then extract characteristics of insurance claims that indicate fraud and identify such characteristics as fraud indicators. (Figure 1; column 9, line 63-67, column 10, line 1-30);
performing machine-learning-based training, at the processor, that allows the catastrophic event detection machine learning model to recognize a catastrophic event by assessing the historical catastrophic event data (column 8, line 14-66, column 9, line 1-67, column 10, line 1-67);
Allerkamp - That is, the insurance computing system 12 may generate or receive a mathematical model by receiving sample data (e.g., insurance claims that have been identified as fraudulent and insurance claims that have been identified as not fraudulent), … That is, the insurance computing system 12 may build a mathematical model by receiving sample data (e.g., information from the client profile 22, claims 20, and/or insurance database 14), predicting the presence of a fraud indicator, and receiving an indication of whether the prediction was true or false. The insurance computing system 12 may then apply the mathematical model to the information received from the insurance database 14 (including the claim 22) and determine a likelihood of whether or not one of the fraud indicators are present…the insurance computing system 12 may use machine learning algorithms to determine the fraud indicators. (column 8, line 14-66, column 9, line 31-67, column 10, line 1-30);
utilizing, at the processor, the catastrophic event detection machine learning model to generate a catastrophic event score, the catastrophic event score being configured to serve as an indicator of the catastrophic event that is used to determine whether to generate a catastrophic-event-based fraud rule (Abstract; column 12, line 6-67, column 13, line 1-67, column 14, line 1-7; claim 9);
Allerkamp - Weighting may be variable and capable of adjustments based on an algorithm (e.g., a learning algorithm), artificial intelligence, an evolutionary algorithm, or the like, which take into account data (e.g., historical data or real-time data) from previous outcomes…. the insurance computing system 12 may generate the risk score by weighting each of the first, second, and third set of fraud indicators and accumulating the weighted fraud indicators. The weights may correspond to a relevance or confidence level of the fraud indicators. That is, if the first set of indicators is more likely to indicate fraud than the second set of indicators, then the first set of indicators may be weighted more heavily … an insurance computing system to autonomously assess the risk of fraud associated with a claim by generating a risk score. The risk score may provide an indication of a likelihood of fraud associated with the claim based on similar insurance claims in the same geographical area, client information indicative of a likelihood to commit fraud, and/or a type of the claim. The insurance computing system may compare the risk score with a threshold number, and if the threshold number is exceeded, the insurance computing system may prompt the client to contact a service representative to further process or validate the claim. (Abstract; column 12, line 45-67);
configuring, at the processor, a financial fraud rule by adjusting the financial fraud rule to yield the catastrophic-event-based fraud rule, the catastrophic -based fraud rule being yielded by adding a catastrophic event threshold to the financial fraud rule; and (Abstract; column 11, line 9-67, column 12, line 1-21, column 13, line 1-67, column 14, line 1-7);
Claim Interpretation – “configuring, at the processor, a financial fraud rule to reduce false declines, the financial fraud rule being configured to reduce false declines by adjusting the financial fraud rule to yield the catastrophic-event-based fraud rule”, the claim recites result language, and therefore has not patentable weight ( Minton v. Nat’l Ass’n of Securities Dealers, Inc., 336 F.3d 1373, 1381, 67 USPQ2d 1614, 1620 (Fed. Cir. 2003)).See MPEP 2111.04. For the purpose of claim interpretation, the positively recited step able to be performed by a processor is “adding a catastrophic event threshold to the financial fraud rule”
Allerkamp - If the threshold risk number is not exceeded, at block 66, the insurance computing system 12 determines that the submitted claim is not fraudulent (e.g., likely not fraudulent) and proceeds to validate the submitted claim, and may eventually make a payout to the client…. The insurance computing system may compare the risk score with a threshold number, and if the threshold number is exceeded, the insurance computing system may prompt the client to contact a service representative to further process or validate the claim. Otherwise, if the threshold number is not exceeded, the insurance computing system may continue processing the claim autonomously…. If the validation process is completed, then the client would eventually receive funds associated with the submitted claim. (Abstract; column 13, line 1-67);
approving, at the processor, using the catastrophic-event-based fraud rule, a payment transaction when the catastrophic event score is below or equal to a catastrophic event threshold, a merchant category code associated with the payment transaction is equal to a catastrophic-event-related-merchant category code, a risk score is below or equal to a predetermined threshold, and a country code is an issuer country code (Abstract; column 4, line 38-67, column 7, line 38-65, column 8, line 4-66, column 13, line 1-67, column 14, line 1-7; claim 9);
Allerkamp - If the threshold risk number is not exceeded, at block 66, the insurance computing system 12 determines that the submitted claim is not fraudulent (e.g., likely not fraudulent) and proceeds to validate the submitted claim, and may eventually make a payout to the client…. The insurance computing system may compare the risk score with a threshold number, and if the threshold number is exceeded, the insurance computing system may prompt the client to contact a service representative to further process or validate the claim. Otherwise, if the threshold number is not exceeded, the insurance computing system may continue processing the claim autonomously…. In one embodiment, the insurance computing system may compare the risk score with a threshold number, and if the threshold number is exceeded, the insurance computing system may prompt the client to contact a service representative (e.g., a live person) to further process or validate the claim…. If the validation process is completed, then the client would eventually receive funds associated with the submitted claim. (Abstract; column 13, line 1-67);
Allerkamp does not disclose selecting, at the processor, based on an assessment of a root mean square error (RMSE), a machine learning model for use as a catastrophic event detection machine learning model.
Elewitz teaches selecting, at the processor, based on an assessment of a root mean square error (RMSE), a machine learning model for use as a catastrophic event detection machine learning model (¶ 151-167);
Elewitz - the risk predictions generated by the complex predictive model to the risk predictions generated by the logistic models. Based on this comparison, the processor determines a root mean square error (RMSE) value between the complex predictive model risk predictions and the logistic model risk predictions. (¶ 165)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Allerkamp(column 14, line 1-7), which teaches “insurance companies may validate an insurance claim while decreasing or minimizing the need for a human adjuster to check for fraud, which leads to a more efficient and streamlined process for clients to receive funds associated with their insurance claims” and Elewitz (¶ 165) which teaches “the risk predictions generated by the complex predictive model to the risk predictions generated by the logistic models” in order to provide a determination of risk during certain types of events with machine learning (Elewitz; ¶ 5).
Regarding claims 3, and 18, Allerkamp discloses determining, with the processor, a start date of the catastrophic event and a location of the catastrophic event based on catastrophic event data (column 5, line 19-43, column 8, line 1-66, column 10, line 59-67).
Regarding claims 4, and 19, Allerkamp discloses wherein: the start date of the catastrophic event and the location of the catastrophic event are used approve a financial transaction as the payment transaction (column 5, line 19-43, column 10, line 47-67).
Regarding claim 16, Allerkamp discloses extract historical catastrophic event data from a network (Figure 1; column 8, line 14-66, column 9, line 1-67, column 10, line 1-67; claim 1, 6);
Allerkamp - At block 54, the insurance computing system 12 identifies similar insurance claims associated with the geographical area. In particular, the insurance computing system 12 may send a query to the insurance database 14 for a subset of the claims 22 that were submitted in the same geographical area. (Figure 1; column 8, line 14-66);
translate the historical catastrophic event data into machine learning feature form ( column 8, line 14-66, column 9, line 1-67, column 10, line 1-67; claim 8, 9);
Allerkamp - the insurance computing system 12 may use machine learning algorithms to determine the fraud indicators. That is, the insurance computing system 12 may generate or receive a mathematical model by receiving sample data (e.g., insurance claims that have been identified as fraudulent and insurance claims that have been identified as not fraudulent), predicting whether an insurance claim of the sample data is fraudulent, and receiving an indication of whether the prediction was true or false. The insurance computing system 12 may then extract characteristics of insurance claims that indicate fraud and identify such characteristics as fraud indicators. (Figure 1; column 9, line 63-67, column 10, line 1-30);
train the catastrophic event detection machine learning model to recognize a catastrophic event by assessing the historical catastrophic event data(column 8, line 14-66, column 9, line 1-67, column 10, line 1-67);
Allerkamp - That is, the insurance computing system 12 may generate or receive a mathematical model by receiving sample data (e.g., insurance claims that have been identified as fraudulent and insurance claims that have been identified as not fraudulent), … That is, the insurance computing system 12 may build a mathematical model by receiving sample data (e.g., information from the client profile 22, claims 20, and/or insurance database 14), predicting the presence of a fraud indicator, and receiving an indication of whether the prediction was true or false. The insurance computing system 12 may then apply the mathematical model to the information received from the insurance database 14 (including the claim 22) and determine a likelihood of whether or not one of the fraud indicators are present…the insurance computing system 12 may use machine learning algorithms to determine the fraud indicators. (column 8, line 14-66, column 9, line 31-67, column 10, line 1-30);
utilize the catastrophic event detection machine learning model to generate a catastrophic event score, the catastrophic event score being configured to serve as an indicator of the catastrophic event that is used to determine whether to generate a catastrophic-event-based fraud rule(Abstract; column 12, line 6-67, column 13, line 1-67, column 14, line 1-7; claim 9);
Allerkamp - Weighting may be variable and capable of adjustments based on an algorithm (e.g., a learning algorithm), artificial intelligence, an evolutionary algorithm, or the like, which take into account data (e.g., historical data or real-time data) from previous outcomes…. the insurance computing system 12 may generate the risk score by weighting each of the first, second, and third set of fraud indicators and accumulating the weighted fraud indicators. The weights may correspond to a relevance or confidence level of the fraud indicators. That is, if the first set of indicators is more likely to indicate fraud than the second set of indicators, then the first set of indicators may be weighted more heavily … an insurance computing system to autonomously assess the risk of fraud associated with a claim by generating a risk score. The risk score may provide an indication of a likelihood of fraud associated with the claim based on similar insurance claims in the same geographical area, client information indicative of a likelihood to commit fraud, and/or a type of the claim. The insurance computing system may compare the risk score with a threshold number, and if the threshold number is exceeded, the insurance computing system may prompt the client to contact a service representative to further process or validate the claim. (Abstract; column 12, line 45-67);
adjust a financial fraud rule to ascertain the catastrophic-event-based fraud rule, the catastrophic-event-based fraud rule being ascertained by adding a catastrophic event threshold to the financial fraud rule; and (Abstract; column 11, line 9-67, column 12, line 1-21, column 13, line 1-67, column 14, line 1-7);
Allerkamp - If the threshold risk number is not exceeded, at block 66, the insurance computing system 12 determines that the submitted claim is not fraudulent (e.g., likely not fraudulent) and proceeds to validate the submitted claim, and may eventually make a payout to the client…. The insurance computing system may compare the risk score with a threshold number, and if the threshold number is exceeded, the insurance computing system may prompt the client to contact a service representative to further process or validate the claim. Otherwise, if the threshold number is not exceeded, the insurance computing system may continue processing the claim autonomously…. If the validation process is completed, then the client would eventually receive funds associated with the submitted claim. (Abstract; column 13, line 1-67);
approve, using the catastrophic-event-based fraud rule, a payment transaction when the catastrophic event score is below or equal to a catastrophic event threshold, a merchant category code associated with the payment transaction is equal to a catastrophic-event-related-merchant category code, a risk score is below or equal to a predetermined threshold, and a country code is an issuer country code (Abstract; column 4, line 38-67, column 7, line 38-65, column 8, line 4-66, column 13, line 1-67, column 14, line 1-7; claim 9);
Allerkamp - If the threshold risk number is not exceeded, at block 66, the insurance computing system 12 determines that the submitted claim is not fraudulent (e.g., likely not fraudulent) and proceeds to validate the submitted claim, and may eventually make a payout to the client…. The insurance computing system may compare the risk score with a threshold number, and if the threshold number is exceeded, the insurance computing system may prompt the client to contact a service representative to further process or validate the claim. Otherwise, if the threshold number is not exceeded, the insurance computing system may continue processing the claim autonomously…. In one embodiment, the insurance computing system may compare the risk score with a threshold number, and if the threshold number is exceeded, the insurance computing system may prompt the client to contact a service representative (e.g., a live person) to further process or validate the claim…. If the validation process is completed, then the client would eventually receive funds associated with the submitted claim. (Abstract; column 13, line 1-67);
Allerkamp does not disclose select, based on an assessment of a root mean square error (RMSE), a machine learning model for use as a catastrophic event detection machine learning model.
Elewitz teaches select, based on an assessment of a root mean square error (RMSE), a machine learning model for use as a catastrophic event detection machine learning model(¶ 151-167);
Elewitz - the risk predictions generated by the complex predictive model to the risk predictions generated by the logistic models. Based on this comparison, the processor determines a root mean square error (RMSE) value between the complex predictive model risk predictions and the logistic model risk predictions. (¶ 165)
utilize machine-learning-based training to train the catastrophic event detection machine learning model to recognize a catastrophic event by assessing the historical catastrophic event data train (¶ 127-130, 151-167; claim 15);
Claim Interpretation – According to the disclosure(¶ 48-54)- “In some embodiments, in order to train the catastrophic event detection machine learning model 331, catastrophic event data extractor 320 extracts historical catastrophic event data 311 from social media resources 361 and/or historical catastrophic event data 312 from news resources 362…. catastrophic event detector 330 receives the catastrophic event data 360 and payment transaction data 390 and uses a machine learning training application to train a machine learning algorithm to output the catastrophic event detection machine learning model 331. In some embodiments, the catastrophic event detection machine learning model 331 output by the machine learning training application is trained to generate the catastrophic event score 370.”
Elewitz - the models in the model data store 309 can be based and/or trained by a training engine 420 according to data (e.g., which may be partitioned into training, testing, and validation data sets) stored in the training data store 411. The training engine 420 can comprise any hardware, software, or combination thereof that can train a predictive model. (¶ 127)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Allerkamp(column 14, line 1-7), which teaches “insurance companies may validate an insurance claim while decreasing or minimizing the need for a human adjuster to check for fraud, which leads to a more efficient and streamlined process for clients to receive funds associated with their insurance claims” and Elewitz (¶ 165) which teaches “the risk predictions generated by the complex predictive model to the risk predictions generated by the logistic models” in order to provide a determination of risk during certain types of events with machine learning (Elewitz; ¶ 5).
Claims 7 and 8 are rejected under 35 U.S.C. 103 as being unpatentable over Allerkamp et al. (US 11,836,803) (“Allerkamp”), in view of Elewitz et al. (US 2021/0110294)(“Elewitz”), and further in view of Adjaoute (US 2019/0213498) (“Adjaoute”).
Regarding claim 7, neither Allerkamp nor Elewitz discloses wherein: the catastrophic-event-related-merchant category code corresponds to merchant category that relates to the catastrophic event. Adjaoute teaches wherein: the catastrophic-event-related-merchant category code corresponds to merchant category that relates to the catastrophic event (¶ 83, 94-99, 108, 109, 117, 139-141, 146). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine Allerkamp, Elewitz and Adjaoute in order to provide a record of fraud transactions towards the end of preventing them (Adjaoute; ¶ 8-11, 94-96).
Regarding claim 8, Adjaoute teaches wherein: in response to determining that the financial transaction is a catastrophic event related transaction, providing, with the at least one processor, a notification to an issuer system to allow the financial transaction to occur (¶ 129, 187, 195, 197).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Dominguez., (US 10460382) teaches payment transaction and fraud detection with merchants.
Duan (US 20150095247) teaches fraud detection with multiple events and event profiles, fraud scores.
Bruckhaus (US 8666829) teaches fraud detection focuses on the events with the payment transactions.
Abadi et al (US 20230030327) teaches non-fraud scores calculated with the payment transaction and the event.
Dixon (US 11741478) teaches machine learning and a catastrophic event.
Knutsson et al (US 2020/0234305) (“Knutsson”) teaches fraud detection with multiple events and event profiles, fraud scores.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ILSE I IMMANUEL whose telephone number is (469)295-9094. The examiner can normally be reached Monday-Friday 9:00 am to 5:00pm.
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, NEHA H PATEL can be reached on (571) 270-1492. 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.
/ILSE I IMMANUEL/Primary Examiner, Art Unit 3699
Prosecution Insights