# US 10,872,339 B1 · Reducing false positives using customer feedback and machine learning > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,872,339 B1 - Document ID: US10872339B1 - Status: Granted - Kind: B1 - Application number: 15/465,832 - Filed: 2017-03-22 - Granted: 2020-12-22 - Earliest claimed: 2016-03-25 - Assignees: State Farm Mutual Automobile Insurance Company - Applicants: State Farm Mutual Automobile Insurance Company - Inventors: Timothy Kramme; Elizabeth Flowers; Reena Batra; Miriam Valero; Puneit Dua; Shanna L. Phillips; Russell Ruestman; Bradley A. Craig - Web page: https://patentgrep.com/patent/US10872339B1 ## CPC - G06Q 30/0185: {Product, service or business identity fraud} - G06N 3/09: Supervised learning - G06N 5/046: Forward inferencing; Production systems - G06N 20/00: Machine learning - G06Q 20/102: {Bill distribution or payments} - G06Q 20/20: Point-of-sale [POS] network systems - G06Q 20/24: Credit schemes, i.e. "pay after" - G06Q 20/3224: {Transactions dependent on location of M-devices} - G06Q 20/34: using cards, e.g. integrated circuit [IC] cards or magnetic cards - G06Q 20/401: {Transaction verification} - G06Q 20/4016: {involving fraud or risk level assessment in transaction processing} - G06Q 20/407: {Cancellation of a transaction} - G06Q 20/409: {Device specific authentication in transaction processing} - G06Q 30/0225: {Avoiding frauds} - G06V 30/194: References adjustable by an adaptive method, e.g. learning - G06V 30/41: Analysis of document content (recognition of printed characters based on code marks G06V30/224) - G06N 3/08: Learning methods - G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06Q 30/0248: {Avoiding fraud} - H04L 2209/56: Financial cryptography, e.g. electronic payment or e-cash - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract A method of reducing a future amount of electronic fraud alerts includes receiving data detailing a financial transaction, inputting the data into a rules-based engine that generates an electronic fraud alert, transmitting the alert to a mobile device of a customer, and receiving from the mobile device customer feedback indicating that the alert was a false positive or otherwise erroneous. The method also includes inputting the data detailing the financial transaction into a machine learning program trained to (i) determine a reason why the false positive was generated, and (ii) then modify the rules-based engine to account for the reason why the false positive was generated, and to no longer generate electronic fraud alerts based upon (a) fact patterns similar to fact patterns of the financial transaction, or (b) data similar to the data detailing the financial transaction, to facilitate reducing an amount of future false positive fraud alerts. ## Claims ### Claim 1 A computer-implemented method of reducing a future amount of electronic fraud alerts generated that are false positives using customer feedback, the method comprising: receiving, by one or both of (i) one or more processors and (ii) one or more transceivers, data detailing a financial transaction associated with a customer, the data detailing the financial transaction being transmitted from a merchant computer terminal over one or more radio links; inputting, by the one or more processors, the data detailing the financial transaction into a rules-based engine that generates an electronic fraud alert based upon the data detailing the financial transaction; transmitting, by one or both of (i) the one or more processors and (ii) the one or more transceivers, the electronic fraud alert to a mobile device of the customer via a wireless communication channel to alert the customer; receiving, by one or both of (i) the one or more processors and (ii) the one or more transceivers, customer feedback from the mobile device of the customer via the wireless communication channel, the customer feedback indicating that the electronic fraud alert was a false positive or otherwise erroneous; and inputting, by the one or more processors, the data detailing the financial transaction into a machine learning program that is trained to (i) determine a reason why the false positive was generated, and (ii) then modify the rules-based engine to account for the reason why the false positive was generated, and to no longer generate electronic fraud alerts based upon (a) fact patterns similar to fact patterns of the financial transaction, or (b) data similar to the data detailing the financial transaction, to facilitate reducing an amount of false positive fraud alerts generated in the future. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein the data detailing the financial transaction includes a credit card number, a card holder name, a merchant name, a transaction or merchant location, and an amount. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, wherein the machine learning program is trained to determine a reason why the false positive was generated at least by training the machine learning program to identify a piece of the data detailing the financial transaction that caused the false positive. ### Claim 4 (depends on 3) The computer-implemented method of claim 3, wherein the identified piece of the data detailing the financial transaction that caused the false positive is a credit card number, a card holder name, a merchant name, a transaction or merchant location, a customer location, or an amount. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein the machine learning program is trained to modify the rules-based engine to no longer generate fraud alerts based upon a same or similar fact pattern as the data detailing the financial transaction, the same or similar fact pattern being determined from a same or similar type of one or more of (i) a card or debit card, (ii) a card issuer, (iii) a credit card number, (iv) a card holder name, (v) a merchant, (vi) a merchant location, (vii) a transaction location, (viii) a transaction amount, or (ix) a type of transaction. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein the machine learning program is trained to determine a reason why the false positive was generated at least by identifying a characteristic of the data detailing the financial transaction that caused the false positive. ### Claim 7 (depends on 6) The computer-implemented method of claim 6, wherein the identified characteristic of the data detailing the financial transaction includes a credit or debit card number, a card holder name, a merchant name, a transaction location, a merchant location, a type of transaction, a customer location, or an amount. ### Claim 8 (depends on 6) The computer-implemented method of claim 6, wherein the identified characteristic of the data detailing the financial transaction includes a transaction amount, a type of the transaction, a location of the transaction or merchant, an identity of a merchant, a type of merchant, or a number or frequency of transactions associated with a merchant or individual. ### Claim 9 (depends on 6) The computer-implemented method of claim 6, wherein the identified characteristic of the data detailing the financial transaction includes one or more inconsistencies between (i) the fact patterns of the financial transaction, and (ii) historical or preferred credit card usage of the customer, or historical financial transactions. ### Claim 10 (depends on 6) The computer-implemented method of claim 6, wherein the identified characteristic of the data detailing the financial transaction includes a previous association between a merchant being used and a data breach. ### Claim 11 (depends on 6) The computer-implemented method of claim 6, wherein the identified characteristic of the data detailing the financial transaction includes an inconsistency between (i) a location of the mobile device of the customer, or a vehicle GPS, at the time of the financial transaction, and (ii) a location of the financial transaction. ### Claim 12 (depends on 6) The computer-implemented method of claim 6, wherein the identified characteristic of the data detailing the financial transaction includes an inconsistency between (i) a home address or city of the customer, and (ii) a location of the financial transaction. ### Claim 13 (depends on 6) The computer-implemented method of claim 6, wherein the identified characteristic of the data detailing the financial transaction includes an inconsistency between (i) a location of the customer at a time of the financial transaction as gleaned from social media, and (ii) a location of the financial transaction. ### Claim 14 (depends on 6) The computer-implemented method of claim 6, wherein the identified characteristic of the data detailing the financial transaction includes that the customer is traveling to a city or state that is not a home address of the customer. ### Claim 15 A computer system configured to reduce a future amount of electronic fraud alerts generated that are false positives using customer feedback, the computer system comprising one or more processors configured to: receive data detailing a financial transaction associated with a customer, the data detailing the financial transaction being transmitted from a merchant computer terminal over one or more radio links; input the data detailing the financial transaction into a rules-based engine that generates an electronic fraud alert based upon the data detailing the financial transaction; transmit the electronic fraud alert to a mobile device of the customer via a wireless communication channel to alert the customer; receive customer feedback from the mobile device of the customer via the wireless communication channel, the customer feedback indicating that the electronic fraud alert was a false positive or otherwise erroneous; and input the data detailing the financial transaction into a machine learning program that is trained to (i) determine a reason why the false positive was generated, and (ii) then modify the rules-based engine to account for the reason why the false positive was generated, and to no longer generate electronic fraud alerts based upon (a) fact patterns similar to fact patterns of the financial transaction, or (b) data similar to the data detailing the financial transaction, to facilitate reducing an amount of false positive fraud alerts generated in the future. ### Claim 16 (depends on 15) The computer system of claim 15, wherein the data detailing the financial transaction includes a credit card number, a card holder name, a merchant name, a transaction or merchant location, and an amount. ### Claim 17 (depends on 15) The computer system of claim 15, wherein the machine learning program is trained to determine a reason why the false positive was generated at least by training the machine learning program to identify a piece of the data detailing the financial transaction that caused the false positive. ### Claim 18 (depends on 15) The computer system of claim 15, wherein the identified piece of the data detailing the financial transaction that caused the false positive is a credit card number, a card holder name, a merchant name, a transaction or merchant location, a customer location, or an amount. ### Claim 19 (depends on 15) The computer system of claim 15, wherein the machine learning program is trained to modify the rules-based engine to no longer generate fraud alerts based upon a same or similar fact pattern as the data detailing the financial transaction, the same or similar fact pattern being determined from a same or similar type of one or more of (i) a card or debit card, (ii) a card issuer, (iii) a credit card number, (iv) a card holder name, (v) a merchant, (vi) a merchant location, (vii) a transaction location, (viii) a transaction amount, or (ix) a type of transaction. ### Claim 20 (depends on 15) The computer system of claim 15, wherein the machine learning program is trained to determine a reason why the false positive was generated at least by identifying a characteristic of the data detailing the financial transaction that caused the false positive. ### Claim 21 (depends on 15) The computer system of claim 15, wherein the machine learning program is trained to modify the rules-based engine by adding a rule or subtracting a rule. ### Claim 22 (depends on 15) The computer system of claim 15, wherein the machine learning program is trained to modify the rules-based engine by adding a rule that checks for data detailing the financial transaction that is similar to one or more facts associated with why the false positive was generated, and when found, directing or otherwise causing the rules-based engine to not generate an electronic fraud alert based solely on those one or more facts.