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 .
DETAILED ACTION
1. The following is a non-Final Office Action in response to applicant’s arguments/filing filed on June 20, 2025
Claims 1-20 are pending
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 4/2/2026 was filed prior to the mailing date of the first office action. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
The information disclosure statement (IDS) submitted on 6/20/2025 was filed prior to the mailing date of the first office action. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Drawings
Acknowledgment is made of applicant’s drawings submitted on 6/20/2025.
Oath/Declaration
Acknowledgment is made of applicant’s oath submitted on 6/20/2025
Application Data Sheet
Acknowledgment is made of applicant’s application data sheet submitted on 6/20/2025.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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 of this title, 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.
1..) Claims 1, 2, 7-9, 15 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over US 20200272740, Obee in view of US 20210398120, Butler
In regards to claim 1, Obee teaches a system comprising: at least one processor(US 20200272740, Obee, para. 0009, the apparatus comprising at least one processor and at least one memory) configured to:receive transaction data associated with at least one transaction associated with an entity(US 20200272740, Obee, para. 0005, determining the transaction data may comprise: processing one or more transaction records to create multiple a plurality of provider-consumer relationships;);determine at least one aggregate value based on at least a portion of the transaction data for the at least one transaction(US 20200272740, Obee, para. 0078, the data analytics computing entity 106 may cause the performance of n parallel processes each configured to determine counts of unique providers for consumers of the multi-provider transactional environment each based on the respective groups of data fields associated with the particular parallel process. Afterward, the data analytics computing entity 106 may aggregate multiple counts of unique providers for a particular consumer each calculated by a respective parallel process to determine an overall count of unique providers for the particular consumer.); Obee does not teach generate at least one predicted aggregate value for the entity by inputting historic transaction data associated with a plurality of historic transactions associated with the entity to a machine learning model;determine a deviation of the at least one aggregate value from the at least one predicted aggregate value;compare the deviation to a dynamic threshold associated with the entity; andin response to determining that the deviation satisfies the dynamic threshold, trigger at least one risk mitigation process associated with the entity However, Butler teaches generate at least one predicted aggregate value for the entity by inputting historic transaction data associated with a plurality of historic transactions associated with the entity to a machine learning model (US 20210398120, Butler, para. 0036 and 0055: [0036]- Predictive model 150 may be developed by machine learning algorithms.[0055]- the future transaction amount may be predicted by transaction patterns and aggregate transaction history data. For example, if the account is completing a promotional rate on a recurring transactions (e.g., with a cable television company or other utility), aggregate transaction data may be used to determine the future transaction amount.);determine a deviation of the at least one aggregate value from the at least one predicted aggregate value (US 20210398120, Butler, fig. 2A, steps 230 and 210, where the predictive model determines if transactional information prediction deviates from a predetermined amount);compare the deviation to a dynamic threshold associated with the entity(US 20210398120, Butler, fig. 2A, steps 210 and 240, where transaction information is compared to a 1st threshold and 2nd threshold values); andin response to determining that the deviation satisfies the dynamic threshold, trigger at least one risk mitigation process associated with the entity(US 20210398120, Butler, fig. 2A and para. 0056 and 0057: [0056]- If the result of the comparison is that the future account balance is less than the second predetermined amount (“YES” path in FIG. 2A at block 240), however, this indicates that there may be additional risk of insufficient funding in the account at the time of the future transaction, and the process may continue on as described below. [0057]- At block 250, a priority score may be determined and assigned to the future transaction. The priority score may be based on a number of factors, including the category of the transaction, account history, user preference information, and method of payment. For example, a future mortgage payment may be considered more important than other transactions of different categories (e.g., a credit card payment) and, thus, may be assigned a higher priority score. As another example, a recurring payment (e.g., a recurring utility payment) may be considered more important than a one-time charge (e.g., for an online purchase) and may be assigned a higher priority score.). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of Obee with the teaching of Butler because a user would have been motivated to use historical data information to train and refine predictive models, taught by Butler, in order to provide more accurate transaction prediction analysis used by Obee(Butler, para. 0055)
In regards to claim 2, the combination of Obee and Butler teach the system of claim 1, wherein, when receiving the transaction data associated with the at least one transaction, the at least one processor is configured to: receive the transaction data associated with the at least one transaction in a first time period(US 20210398120, Butler, para. 0007, determining if the account balance is less than a first predetermined amount; applying a predictive model to the recorded transactions to determine a future transaction that is likely to occur within a predetermined time period after the determining that the account balance is less than the first predetermined amount;); and wherein the at least one processor is further configured to:receive the historic transaction data associated with the plurality of historic transactions in a training time period preceding the first time period(US 20210398120, Butler, para. 0049, The first predetermined amount may be based on one or more factors such as an historic average account balance or an average balance over a predetermined time period (such as, e.g., a 3-month period), or an estimate of funds as required to pay all expected bills due within a time period (such as, e.g., within the next 30 days), and may be adjusted over time.);determine at least one historic aggregate value based on at least a portion of the historic transaction data for the plurality of historic transactions, based on a type of entity associated with the plurality of historic transactions(US 20210398120, Butler, para. 0055, the future transaction amount may be predicted by transaction patterns and aggregate transaction history data. For example, if the account is completing a promotional rate on a recurring transactions (e.g., with a cable television company[i.e. note: entity] or other utility), aggregate transaction data may be used to determine the future transaction amount.); and train the machine learning model with the at least one historic aggregate value, wherein the machine learning model is configured to predict at least one future value of transaction data for future transactions(US 20210398120, Butler, para. 0036, it is understood that other machine learning algorithms may be utilized. In some embodiments, the predictive model may be developed and trained using historical data associated with user transactions and accounts. In some embodiments, the historical data associated with user transactions and accounts may include data associated with a plurality of users, or may be from a category or sub-category of users (e.g., users sharing a particular profession, users having a particular range of income, or users who are high spenders)).
In regards to claim 7, Obee teaches a computer-implemented method, comprising: receiving, with at least one processor, transaction data associated with at least one transaction associated with an entity(US 20200272740, Obee, para. 0005, determining the transaction data may comprise: processing one or more transaction records to create multiple a plurality of provider-consumer relationships;); determining, with at least one processor, at least one aggregate value based on at least a portion of the transaction data for the at least one transaction(US 20200272740, Obee, para. 0078, the data analytics computing entity 106 may cause the performance of n parallel processes each configured to determine counts of unique providers for consumers of the multi-provider transactional environment each based on the respective groups of data fields associated with the particular parallel process. Afterward, the data analytics computing entity 106 may aggregate multiple counts of unique providers for a particular consumer each calculated by a respective parallel process to determine an overall count of unique providers for the particular consumer.); Obee does not teach generating, with at least one processor, at least one predicted aggregate value for the entity by inputting historic transaction data associated with a plurality of historic transactions associated with the entity to a machine learning model;determining, with at least one processor, a deviation of the at least one aggregate value from the at least one predicted aggregate value;comparing, with at least one processor, the deviation to a dynamic threshold associated with the entity; andin response to determining that the deviation satisfies the dynamic threshold, triggering, with at least one processor, at least one risk mitigation process associated with the entity However, Butler teaches generating, with at least one processor, at least one predicted aggregate value for the entity by inputting historic transaction data associated with a plurality of historic transactions associated with the entity to a machine learning model(US 20210398120, Butler, para. 0036 and 0055: [0036]- Predictive model 150 may be developed by machine learning algorithms.[0055]- the future transaction amount may be predicted by transaction patterns and aggregate transaction history data. For example, if the account is completing a promotional rate on a recurring transactions (e.g., with a cable television company or other utility), aggregate transaction data may be used to determine the future transaction amount.);determining, with at least one processor, a deviation of the at least one aggregate value from the at least one predicted aggregate value(US 20210398120, Butler, fig. 2A, steps 230 and 210, where the predictive model determines if transactional information prediction deviates from a predetermined amount);comparing, with at least one processor, the deviation to a dynamic threshold associated with the entity(US 20210398120, Butler, fig. 2A, steps 210 and 240, where transaction information is compared to a 1st threshold and 2nd threshold values); andin response to determining that the deviation satisfies the dynamic threshold, triggering, with at least one processor, at least one risk mitigation process associated with the entity(US 20210398120, Butler, fig. 2A and para. 0056 and 0057: [0056]- If the result of the comparison is that the future account balance is less than the second predetermined amount (“YES” path in FIG. 2A at block 240), however, this indicates that there may be additional risk of insufficient funding in the account at the time of the future transaction, and the process may continue on as described below. [0057]- At block 250, a priority score may be determined and assigned to the future transaction. The priority score may be based on a number of factors, including the category of the transaction, account history, user preference information, and method of payment. For example, a future mortgage payment may be considered more important than other transactions of different categories (e.g., a credit card payment) and, thus, may be assigned a higher priority score. As another example, a recurring payment (e.g., a recurring utility payment) may be considered more important than a one-time charge (e.g., for an online purchase) and may be assigned a higher priority score.). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of Obee with the teaching of Butler because a user would have been motivated to use historical data information to train and refine predictive models, taught by Butler, in order to provide more accurate transaction prediction analysis used by Obee(Butler, para. 0055)
In regards to claim 8, the combination of Obee and Butler teach the computer-implemented method of claim 7, wherein receiving the transaction data associated with the at least one transaction comprises: receiving the transaction data associated with the at least one transaction in a first time period(US 20210398120, Butler, para. 0007, determining if the account balance is less than a first predetermined amount; applying a predictive model to the recorded transactions to determine a future transaction that is likely to occur within a predetermined time period after the determining that the account balance is less than the first predetermined amount;); the method further comprising:receiving, with at least one processor, the historic transaction data associated with the plurality of historic transactions in a training time period preceding the first time period(US 20210398120, Butler, para. 0049, The first predetermined amount may be based on one or more factors such as an historic average account balance or an average balance over a predetermined time period (such as, e.g., a 3-month period), or an estimate of funds as required to pay all expected bills due within a time period (such as, e.g., within the next 30 days), and may be adjusted over time.);determining, the at least one processor, at least one historic aggregate value based on at least a portion of the historic transaction data for the plurality of historic transactions, based on a type of entity associated with the plurality of historic transactions(US 20210398120, Butler, para. 0055, the future transaction amount may be predicted by transaction patterns and aggregate transaction history data. For example, if the account is completing a promotional rate on a recurring transactions (e.g., with a cable television company[i.e. note: entity] or other utility), aggregate transaction data may be used to determine the future transaction amount.); andtraining, with at least one processor, the machine learning model with the at least one historic aggregate value, wherein the machine learning model is configured to predict at least one future value of transaction data for future transactions(US 20210398120, Butler, para. 0036, it is understood that other machine learning algorithms may be utilized. In some embodiments, the predictive model may be developed and trained using historical data associated with user transactions and accounts. In some embodiments, the historical data associated with user transactions and accounts may include data associated with a plurality of users, or may be from a category or sub-category of users (e.g., users sharing a particular profession, users having a particular range of income, or users who are high spenders)).
In regards to claim 9, the combination of Obee and Butler teach the computer-implemented method of claim 7, wherein a type of the entity comprises at least one of: transaction account, merchant, acquirer, issuer, or any combination thereof(US 20210398120, Butler, para. 0008, Embodiments of the present disclosure provide An artificial intelligence system, comprising: a database containing transaction information associated with a user account, wherein the transaction information includes one or more of a transaction amount, account balance, transaction date, merchant name, and merchant category;).
In regards to claim 15, Obee teaches a computer program product comprising at least one non- transitory computer-readable medium comprising program instructions that, when executed by at least one processor, cause the at least one processor to: receive transaction data associated with at least one transaction associated with an entity(US 20200272740, Obee, para. 0005, determining the transaction data may comprise: processing one or more transaction records to create multiple a plurality of provider-consumer relationships;);determine at least one aggregate value based on at least a portion of the transaction data for the at least one transaction(US 20200272740, Obee, para. 0078, the data analytics computing entity 106 may cause the performance of n parallel processes each configured to determine counts of unique providers for consumers of the multi-provider transactional environment each based on the respective groups of data fields associated with the particular parallel process. Afterward, the data analytics computing entity 106 may aggregate multiple counts of unique providers for a particular consumer each calculated by a respective parallel process to determine an overall count of unique providers for the particular consumer.); Obee does not teach generate at least one predicted aggregate value for the entity by inputting historic transaction data associated with a plurality of historic transactions associated with the entity to a machine learning model;determine a deviation of the at least one aggregate value from the at least one predicted aggregate value;compare the deviation to a dynamic threshold associated with the entity; and in response to determining that the deviation satisfies the dynamic threshold, trigger at least one risk mitigation process associated with the entity However, Butler teaches generate at least one predicted aggregate value for the entity by inputting historic transaction data associated with a plurality of historic transactions associated with the entity to a machine learning model(US 20210398120, Butler, para. 0036 and 0055: [0036]- Predictive model 150 may be developed by machine learning algorithms.[0055]- the future transaction amount may be predicted by transaction patterns and aggregate transaction history data. For example, if the account is completing a promotional rate on a recurring transactions (e.g., with a cable television company or other utility), aggregate transaction data may be used to determine the future transaction amount.);determine a deviation of the at least one aggregate value from the at least one predicted aggregate value(US 20210398120, Butler, fig. 2A, steps 230 and 210, where the predictive model determines if transactional information prediction deviates from a predetermined amount);compare the deviation to a dynamic threshold associated with the entity(US 20210398120, Butler, fig. 2A, steps 210 and 240, where transaction information is compared to a 1st threshold and 2nd threshold values); and in response to determining that the deviation satisfies the dynamic threshold, trigger at least one risk mitigation process associated with the entity(US 20210398120, Butler, fig. 2A and para. 0056 and 0057: [0056]- If the result of the comparison is that the future account balance is less than the second predetermined amount (“YES” path in FIG. 2A at block 240), however, this indicates that there may be additional risk of insufficient funding in the account at the time of the future transaction, and the process may continue on as described below. [0057]- At block 250, a priority score may be determined and assigned to the future transaction. The priority score may be based on a number of factors, including the category of the transaction, account history, user preference information, and method of payment. For example, a future mortgage payment may be considered more important than other transactions of different categories (e.g., a credit card payment) and, thus, may be assigned a higher priority score. As another example, a recurring payment (e.g., a recurring utility payment) may be considered more important than a one-time charge (e.g., for an online purchase) and may be assigned a higher priority score.). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of Obee with the teaching of Butler because a user would have been motivated to use historical data information to train and refine predictive models, taught by Butler, in order to provide more accurate transaction prediction analysis used by Obee(Butler, para. 0055)
In regards to claim 16, the combination of Obee and Butler teach the computer program product of claim 15, wherein the program instructions that cause the at least one processor to receive the transaction data associated with the at least one transaction, cause the at least one processor to: receive the transaction data associated with the at least one transaction in a first time period(US 20210398120, Butler, para. 0007, determining if the account balance is less than a first predetermined amount; applying a predictive model to the recorded transactions to determine a future transaction that is likely to occur within a predetermined time period after the determining that the account balance is less than the first predetermined amount;); and wherein the program instructions further cause the at least one processor to:receive the historic transaction data associated with the plurality of historic transactions in a training time period preceding the first time period(US 20210398120, Butler, para. 0049, The first predetermined amount may be based on one or more factors such as an historic average account balance or an average balance over a predetermined time period (such as, e.g., a 3-month period), or an estimate of funds as required to pay all expected bills due within a time period (such as, e.g., within the next 30 days), and may be adjusted over time.);determine at least one historic aggregate value based on at least a portion of the historic transaction data for the plurality of historic transactions, based on a type of entity associated with the plurality of historic transactions(US 20210398120, Butler, para. 0055, the future transaction amount may be predicted by transaction patterns and aggregate transaction history data. For example, if the account is completing a promotional rate on a recurring transactions (e.g., with a cable television company[i.e. note: entity] or other utility), aggregate transaction data may be used to determine the future transaction amount.); and train the machine learning model with the at least one historic aggregate value, wherein the machine learning model is configured to predict at least one future value of transaction data for future transactions(US 20210398120, Butler, para. 0036, it is understood that other machine learning algorithms may be utilized. In some embodiments, the predictive model may be developed and trained using historical data associated with user transactions and accounts. In some embodiments, the historical data associated with user transactions and accounts may include data associated with a plurality of users, or may be from a category or sub-category of users (e.g., users sharing a particular profession, users having a particular range of income, or users who are high spenders)).
2.) Claims 3, 4, 10, 11, 17, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over US 20200272740, Obee in view of US 20210398120, Butler and further in view of US 20230177512, Laptiev
In regards to claim 3, the combination of Obee and Butler teach the system of claim 1, wherein a type of the entity comprises at least one of: transaction account, merchant, acquirer, issuer, or any combination thereof(US 20210398120, Butler, para. 0008, Embodiments of the present disclosure provide An artificial intelligence system, comprising: a database containing transaction information associated with a user account, wherein the transaction information includes one or more of a transaction amount, account balance, transaction date, merchant name, and merchant category;); and The combination of Obee and Butler do not teach wherein the at least one risk mitigation process comprises at least one of: temporarily declining future transactions associated with the entity, transmitting an alert to the entity, temporarily disabling system access for the entity, or any combination thereof However, Laptiev teaches wherein the at least one risk mitigation process comprises at least one of: temporarily declining future transactions associated with the entity, transmitting an alert to the entity, temporarily disabling system access for the entity, or any combination thereof (US 20230177512, Laptiev, para. 0024, the intelligent fraud detection system can provide notifications or other visual indicators of a fraud prediction and execute various authorizing or remedial actions based on the fraud prediction. For instance, the intelligent fraud detection system can determine that the fraud prediction exceeds a high-risk fraud prediction threshold, indicating a high probability that the digital claim is fraudulent. The intelligent fraud detection system can then provide a high-risk visual indicator for display, denoting a high likelihood of fraud for the digital claim. Based on the fraud prediction exceeding the high-risk fraud prediction threshold, the intelligent fraud detection system can suspend one or both of a network transaction associated and an account associated with the digital claim.). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of the combination of Obee and Butler with the teaching of Laptiev because a user would have been motivated to fraud detection machine-learning model, taught by Laptiev, in order to provide transactional security in the system taught by the combination of Obee and Butler(Laptiev, para. 0007)
In regards to claim 4, the combination of Obee and Butler teach the system of claim 1. The combination of Obee and Butler do not teach wherein the at least one processor is further configured to automatically and periodically update the dynamic threshold based on ongoing transactions associated with the entity However, Laptiev teaches wherein the at least one processor is further configured to automatically and periodically update the dynamic threshold based on ongoing transactions associated with the entity(US 20230177512, Laptiev, fig. 9 and para. 0107, the graph 902 depicts curves representing the values of various probability metrics over an increasing threshold value.). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of the combination of Obee and Butler with the teaching of Laptiev because a user would have been motivated to fraud detection machine-learning model, taught by Laptiev, in order to provide transactional security in the system taught by the combination of Obee and Butler(Laptiev, para. 0007)
In regards to claim 10, the combination of Obee and Butler teach the computer-implemented method of claim 9. the combination of Obee and Butler do not teach wherein the at least one risk mitigation process comprises at least one of: temporarily declining future transactions associated with the entity, transmitting an alert to the entity, temporarily disabling system access for the entity, or any combination thereof However, Laptiev teaches wherein the at least one risk mitigation process comprises at least one of: temporarily declining future transactions associated with the entity, transmitting an alert to the entity, temporarily disabling system access for the entity, or any combination thereof (US 20230177512, Laptiev, para. 0024, the intelligent fraud detection system can provide notifications or other visual indicators of a fraud prediction and execute various authorizing or remedial actions based on the fraud prediction. For instance, the intelligent fraud detection system can determine that the fraud prediction exceeds a high-risk fraud prediction threshold, indicating a high probability that the digital claim is fraudulent. The intelligent fraud detection system can then provide a high-risk visual indicator for display, denoting a high likelihood of fraud for the digital claim. Based on the fraud prediction exceeding the high-risk fraud prediction threshold, the intelligent fraud detection system can suspend one or both of a network transaction associated and an account associated with the digital claim.). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of the combination of Obee and Butler with the teaching of Laptiev because a user would have been motivated to fraud detection machine-learning model, taught by Laptiev, in order to provide transactional security in the system taught by the combination of Obee and Butler(Laptiev, para. 0007)
In regards to claim 11, the combination of Obee and Butler teach the computer-implemented method of claim 7. The combination of Obee and Butler do not teach further comprising automatically and periodically updating, with at least one processor, the dynamic threshold based on ongoing transactions associated with the entity However, Laptiev teaches further comprising automatically and periodically updating, with at least one processor, the dynamic threshold based on ongoing transactions associated with the entity(US 20230177512, Laptiev, fig. 9 and para. 0107, the graph 902 depicts curves representing the values of various probability metrics over an increasing threshold value.). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of the combination of Obee and Butler with the teaching of Laptiev because a user would have been motivated to fraud detection machine-learning model, taught by Laptiev, in order to provide transactional security in the system taught by the combination of Obee and Butler(Laptiev, para. 0007)
In regards to claim 17, the combination of Obee and Butler teach the computer program product of claim 15, wherein a type of the entity comprises at least one of: transaction account, merchant, acquirer, issuer, or any combination thereof(US 20210398120, Butler, para. 0008, Embodiments of the present disclosure provide An artificial intelligence system, comprising: a database containing transaction information associated with a user account, wherein the transaction information includes one or more of a transaction amount, account balance, transaction date, merchant name, and merchant category;); and the combination of Obee and Butler do not teach wherein the at least one risk mitigation process comprises at least one of: temporarily declining future transactions associated with the entity, transmitting an alert to the entity, temporarily disabling system access for the entity, or any combination thereof However, Laptiev teaches wherein the at least one risk mitigation process comprises at least one of: temporarily declining future transactions associated with the entity, transmitting an alert to the entity, temporarily disabling system access for the entity, or any combination thereof(US 20230177512, Laptiev, para. 0024, the intelligent fraud detection system can provide notifications or other visual indicators of a fraud prediction and execute various authorizing or remedial actions based on the fraud prediction. For instance, the intelligent fraud detection system can determine that the fraud prediction exceeds a high-risk fraud prediction threshold, indicating a high probability that the digital claim is fraudulent. The intelligent fraud detection system can then provide a high-risk visual indicator for display, denoting a high likelihood of fraud for the digital claim. Based on the fraud prediction exceeding the high-risk fraud prediction threshold, the intelligent fraud detection system can suspend one or both of a network transaction associated and an account associated with the digital claim.). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of the combination of Obee and Butler with the teaching of Laptiev because a user would have been motivated to fraud detection machine-learning model, taught by Laptiev, in order to provide transactional security in the system taught by the combination of Obee and Butler(Laptiev, para. 0007)
In regards to claim 18, the combination of Obee and Butler teach the computer program product of claim 15. The combination of Obee and Butler do not teach wherein the program instructions further cause the at least one processor to automatically and periodically update the dynamic threshold based on ongoing transactions associated with the entity However, Laptiev teaches wherein the program instructions further cause the at least one processor to automatically and periodically update the dynamic threshold based on ongoing transactions associated with the entity(US 20230177512, Laptiev, fig. 9 and para. 0107, the graph 902 depicts curves representing the values of various probability metrics over an increasing threshold value.). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of the combination of Obee and Butler with the teaching of Laptiev because a user would have been motivated to fraud detection machine-learning model, taught by Laptiev, in order to provide transactional security in the system taught by the combination of Obee and Butler(Laptiev, para. 0007)
3.) Claims 5, 6, 12, 13, 19, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over US 20200272740, Obee in view of US 20210398120, Butler and further in view of US 20230177512, Laptiev and further in view of US 20220067510, Jayakumar and further in view of US 20080077515, Zoldi
In regards to claim 5, the combination of Obee, Butler and Laptiev teach the system of claim 4. The combination of Obee, Butler and Laptiev do not teach wherein the deviation is based at least partly on a moving standard deviation, and wherein, when updating the dynamic threshold based on the ongoing transactions associated with the entity, the at least one processor is configured to: determine the deviation of the at least one aggregate value from the at least one predicted aggregate value for each subperiod of a time period in which the ongoing transactions are completed, to produce a plurality of deviations However, Jayakumar teaches wherein the deviation is based at least partly on a moving standard deviation, and wherein, when updating the dynamic threshold based on the ongoing transactions associated with the entity, the at least one processor is configured to: determine the deviation of the at least one aggregate value from the at least one predicted aggregate value for each subperiod of a time period in which the ongoing transactions are completed, to produce a plurality of deviations(US 20220067510, Jayakumar, para. 0013, a system for predicting user events associated with a user may access data (also referred to as data items) associated with the user. The data may be based on historical data related to interactions between the user and the service provider…An aggregate value may combine the value of data associated with the feature over a time interval. For example, one aggregate value may be the sum of all purchases in a week or the average amount (e.g., arithmetic mean) spent per day over a week, and another aggregate value may be the number of payment authorizations in a week. Each aggregate value may be standardized by subtracting the arithmetic mean of corresponding aggregate values from a set of training data and dividing the result by the standard deviation of the corresponding aggregate values from the training data.); It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of the combination of Obee, Butler, and Laptiev with the teaching of Jayakumar because a user would have been motivated to use a long short-term memory, taught by Jayakumar, to predict user transactional behavior in order to determine the likelihood of a user, in the system taught by the combination of Obee, Butler, and Laptiev, is to engage in defaulting on a transactional obligation(Jayakumar, para. 0014) the combination of Obee, Butler, Laptiev and Jayakumar do not teach update the dynamic threshold after each subperiod of the time period based at least partly on a maximum value of the plurality of deviations However, Zoldi teaches update the dynamic threshold after each subperiod of the time period based at least partly on a maximum value of the plurality of deviations (US 20080077515, Zoldi, para. 0042, a maximum expected (or received) transaction value is labeled as parameter x.sub.max. In FIG. 3, a 99th percentile threshold parameter 340 is associated with x.sub.max and has a value of fifteen hours.) It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of the combination of Obee, Butler, Laptiev and Jayakumar with the teaching of Zoldi because a user would have been motivated to use dynamic real-time updating of variables of a transactional model, taught by Zoldi, in order to improve fraud detection when historical data is limited or nonexistent in the system taught by the combination of Obee, Butler, Laptiev and Jayakumar(Zoldi, para. 0010).
In regards to claim 6, the combination of Obee, Butler, Laptiev, Jayakumar, and Zoldi teach the system of claim 5, wherein the at least one processor is further configured to retrain the machine learning model based on the ongoing transactions to produce an updated machine learning model(US 20210398120, Butler, para. 0035, Predictive model 150 may include continuous learning capabilities that allow the model to adjust itself or its determinations as more information and data becomes available.), and wherein, when determining the deviation of the at least one aggregate value from the at least one predicted aggregate value for each subperiod of the time period, the at least one processor is configured to: regenerate the at least one predicted aggregate value for the entity based on the updated machine learning model(US 20210398120, Butler, para. 0008, 0037 and 0055: [0008]- monitor transaction information to determine the accuracy of the predictive model; and adjust the predictive model in response to the determined accuracy;[0037]- The machine learning may then apply the generated models to predict future transactions and future account balances.[0055]- the future transaction amount may be predicted by transaction patterns and aggregate transaction history data. For example, if the account is completing a promotional rate on a recurring transactions (e.g., with a cable television company or other utility), aggregate transaction data may be used to determine the future transaction amount.[i.e. note: upon adjustments to a predictive model, an updated aggregate value may implicitly may be generated]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of the combination of Obee, Laptiev, Jayakumar, and Zoldi with the teaching of Butler because a user would have been motivated to use historical data information to train and refine predictive models, taught by Butler, in order to provide more accurate transaction prediction analysis used by Obee(Butler, para. 0055).
In regard to claim 12, the combination of Obee, Butler and Laptiev teach the computer-implemented method of claim 11. The combination of Obee, Butler and Laptiev do not teach wherein the deviation is based at least partly on a moving standard deviation, and wherein updating the dynamic threshold based on the ongoing transactions associated with the entity comprises: determining the deviation of the at least one aggregate value from the at least one predicted aggregate value for each subperiod of a time period in which the ongoing transactions are completed, to produce a plurality of deviations However, Jayakumar teaches wherein the deviation is based at least partly on a moving standard deviation, and wherein updating the dynamic threshold based on the ongoing transactions associated with the entity comprises: determining the deviation of the at least one aggregate value from the at least one predicted aggregate value for each subperiod of a time period in which the ongoing transactions are completed, to produce a plurality of deviations(US 20220067510, Jayakumar, para. 0013, a system for predicting user events associated with a user may access data (also referred to as data items) associated with the user. The data may be based on historical data related to interactions between the user and the service provider…An aggregate value may combine the value of data associated with the feature over a time interval. For example, one aggregate value may be the sum of all purchases in a week or the average amount (e.g., arithmetic mean) spent per day over a week, and another aggregate value may be the number of payment authorizations in a week. Each aggregate value may be standardized by subtracting the arithmetic mean of corresponding aggregate values from a set of training data and dividing the result by the standard deviation of the corresponding aggregate values from the training data.); It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of the combination of Obee, Butler, and Laptiev with the teaching of Jayakumar because a user would have been motivated to use a long short-term memory, taught by Jayakumar, to predict user transactional behavior in order to determine the likelihood of a user, in the system taught by the combination of Obee, Butler, and Laptiev, is to engage in defaulting on a transactional obligation(Jayakumar, para. 0014)and the combination of Obee, Butler, Laptiev and Jayakumar do not teach updating the dynamic threshold after each subperiod of the time period based at least partly on a maximum value of the plurality of deviations However, Zoldi teaches updating the dynamic threshold after each subperiod of the time period based at least partly on a maximum value of the plurality of deviations (US 20080077515, Zoldi, para. 0042, a maximum expected (or received) transaction value is labeled as parameter x.sub.max. In FIG. 3, a 99th percentile threshold parameter 340 is associated with x.sub.max and has a value of fifteen hours.). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of the combination of Obee, Butler, Laptiev and Jayakumar with the teaching of Zoldi because a user would have been motivated to use dynamic real-time updating of variables of a transactional model, taught by Zoldi, in order to improve fraud detection when historical data is limited or nonexistent in the system taught by the combination of Obee, Butler, Laptiev and Jayakumar(Zoldi, para. 0010)
In regards to claim 13, the combination of Obee, Butler, Laptiev, Jayakumar and Zoldi teach the computer-implemented method of claim 12, further comprising retraining, with at least one processor, the machine learning model based on the ongoing transactions to produce an updated machine learning model(US 20210398120, Butler, para. 0035, Predictive model 150 may include continuous learning capabilities that allow the model to adjust itself or its determinations as more information and data becomes available.), wherein determining the deviation of the at least one aggregate value from the at least one predicted aggregate value for each subperiod of the time period further comprises: regenerating, during the time period, the at least one predicted aggregate value for the entity based on the updated machine learning model(US 20210398120, Butler, para. 0008, 0037 and 0055: [0008]- monitor transaction information to determine the accuracy of the predictive model; and adjust the predictive model in response to the determined accuracy;[0037]- The machine learning may then apply the generated models to predict future transactions and future account balances.[0055]- the future transaction amount may be predicted by transaction patterns and aggregate transaction history data. For example, if the account is completing a promotional rate on a recurring transactions (e.g., with a cable television company or other utility), aggregate transaction data may be used to determine the future transaction amount.[i.e. note: upon adjustments to a predictive model, an updated aggregate value may implicitly may be generated]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of the combination of Obee, Laptiev, Jayakumar, and Zoldi with the teaching of Butler because a user would have been motivated to use historical data information to train and refine predictive models, taught by Butler, in order to provide more accurate transaction prediction analysis used by Obee(Butler, para. 0055)
In regards to claim 19, the combination of Obee, Butler and Laptiev teach the computer program product of claim 18. The combination of Obee, Butler and Laptiev do not teach wherein the deviation is based at least partly on a moving standard deviation, and wherein the program instructions that cause the at least one processor to update the dynamic threshold based on the ongoing transactions associated with the entity, cause the at least one processor to: determine the deviation of the at least one aggregate value from the at least one predicted aggregate value for each subperiod of a time period in which the ongoing transactions are completed, to produce a plurality of deviations However, Jayakumar teaches wherein the deviation is based at least partly on a moving standard deviation, and wherein the program instructions that cause the at least one processor to update the dynamic threshold based on the ongoing transactions associated with the entity, cause the at least one processor to: determine the deviation of the at least one aggregate value from the at least one predicted aggregate value for each subperiod of a time period in which the ongoing transactions are completed, to produce a plurality of deviations(US 20220067510, Jayakumar, para. 0013, a system for predicting user events associated with a user may access data (also referred to as data items) associated with the user. The data may be based on historical data related to interactions between the user and the service provider…An aggregate value may combine the value of data associated with the feature over a time interval. For example, one aggregate value may be the sum of all purchases in a week or the average amount (e.g., arithmetic mean) spent per day over a week, and another aggregate value may be the number of payment authorizations in a week. Each aggregate value may be standardized by subtracting the arithmetic mean of corresponding aggregate values from a set of training data and dividing the result by the standard deviation of the corresponding aggregate values from the training data.); It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of the combination of Obee, Butler, and Laptiev with the teaching of Jayakumar because a user would have been motivated to use a long short-term memory, taught by Jayakumar, to predict user transactional behavior in order to determine the likelihood of a user, in the system taught by the combination of Obee, Butler, and Laptiev, is to engage in defaulting on a transactional obligation(Jayakumar, para. 0014)and the combination of Obee, Butler, Laptiev and Jayakumar do not teach teach update the dynamic threshold after each subperiod of the time period based at least partly on a maximum value of the plurality of deviations However, Zoldi teaches teach update the dynamic threshold after each subperiod of the time period based at least partly on a maximum value of the plurality of deviations(US 20080077515, Zoldi, para. 0042, a maximum expected (or received) transaction value is labeled as parameter x.sub.max. In FIG. 3, a 99th percentile threshold parameter 340 is associated with x.sub.max and has a value of fifteen hours.) It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of the combination of Obee, Butler, Laptiev and Jayakumar with the teaching of Zoldi because a user would have been motivated to use dynamic real-time updating of variables of a transactional model, taught by Zoldi, in order to improve fraud detection when historical data is limited or nonexistent in the system taught by the combination of Obee, Butler, Laptiev and Jayakumar(Zoldi, para. 0010).
In regards to claim 20, the combination of Obee, Butler, Laptiev, Jayakumar and Zoldi teach the computer program product of claim 19, wherein the program instructions further cause the at least one processor to retrain the machine learning model based on the ongoing transactions to produce an updated machine learning model(US 20210398120, Butler, para. 0035, Predictive model 150 may include continuous learning capabilities that allow the model to adjust itself or its determinations as more information and data becomes available.), and wherein the program instructions that cause the at least one processor to determine the deviation of the at least one aggregate value from the at least one predicted aggregate value for each subperiod of the time period, cause the at least one processor to: regenerate the at least one predicted aggregate value for the entity based on the updated machine learning model(US 20210398120, Butler, para. 0008, 0037 and 0055: [0008]- monitor transaction information to determine the accuracy of the predictive model; and adjust the predictive model in response to the determined accuracy;[0037]- The machine learning may then apply the generated models to predict future transactions and future account balances.[0055]- the future transaction amount may be predicted by transaction patterns and aggregate transaction history data. For example, if the account is completing a promotional rate on a recurring transactions (e.g., with a cable television company or other utility), aggregate transaction data may be used to determine the future transaction amount.[i.e. note: upon adjustments to a predictive model, an updated aggregate value may implicitly may be generated]). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of the combination of Obee, Laptiev, Jayakumar, and Zoldi with the teaching of Butler because a user would have been motivated to use historical data information to train and refine predictive models, taught by Butler, in order to provide more accurate transaction prediction analysis used by Obee(Butler, para. 0055)
4.) Claim 14 is rejected under 35 U.S.C. 103 as being unpatentable over US 20200272740, Obee in view of US 20210398120, Butler and further in view of US 20220067510, Jayakumar
In regards to claim 14, the combination of Obee and Butler teach the computer-implemented method of claim 7. The combination of Obee and Butler do not teach wherein the machine learning model is a long short-term memory (LSTM) model However, Jayakumar teaches wherein the machine learning model is a long short-term memory (LSTM) model(US 20220067510, Jayakumar, para. 0036, The decision engine server 150 is configured to determine whether user account records should be tagged and includes a neural network 152 (illustrated in detail in FIG. 3), a training module 154, and a prediction module 156. The decision engine server may communicate with the decision engine data store 158, which stores account data received from the service provider server 130 (e.g., from the data collection module) for processing. Neural network 152 may be an LSTM neural network.). It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teaching of the combination of Obee, Butler, and Laptiev with the teaching of Jayakumar because a user would have been motivated to use a long short-term memory, taught by Jayakumar, to predict user transactional behavior in order to determine the likelihood of a user, in the system taught by the combination of Obee and Butler is to engage in defaulting on a transactional obligation(Jayakumar, para. 0014)
CONCLUSION
Any inquiry concerning this communication or earlier communications from the examiner should be directed to GREGORY LANE whose telephone number is (571)270-7469. The examiner can normally be reached on 571 270 7469 from 8:00 AM to 6:00 PM.
If attempts to reach the examiner by telephone are unsuccessful, the examiner's supervisor, Taghi Arani, can be reached on 571 272 3787. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
/GREGORY A LANE/Examiner, Art Unit 2438
/TAGHI T ARANI/Supervisory Patent Examiner, Art Unit 2438
Prosecution Insights