IP Library › Granted Patent US 12,614,196
Granted Patent B2
US 12,614,196 · App. 18/625,304 · Granted Apr 28, 2026

Systems and methods to manage transaction disputes using predictions based on anomalous data

Inventors: Jeffrey Paul Kubler (Birmingham, AL); Shane Saunders (Milwaukee, WI); Joseph Fredric Sutthoff (Matthews, NC); Joe Leung (Sacramento, CA); Lauren Morrison (Jacksonville, FL); Matthew Petersen (Apex, NC); David Raynault (Winter Springs, FL); Philip J. Ponsaran (Fremont, CA)
Assignee: Fidelity Information Services, LLC
G06Q30/0185G06F9/547G06F16/2365G06F16/2379G06N5/04G06N20/00G06Q20/201G06Q20/209G06Q40/02H04L67/306H04L67/535G06F3/0483
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,614,196
App. No.
18/625,304
Filed
Apr 3, 2024
Granted
Apr 28, 2026
Kind
B2
Art Unit
2446
USPC
705/20
Abstract

Disclosed herein are systems and methods for managing transaction disputes. Techniques include accessing a transaction pattern model associated with a user account; detecting deviation of a transaction from the transaction pattern model; transmitting, based on the detected deviation, transaction data to a user device; receiving an input at the user device in response to the transmitted data; generating, based on the received input, dispute data; storing the dispute data; monitoring data extracts associated with the user account; detecting, based on the monitoring, a data extract indicating a posted state of a transaction associated with the dispute data; and updating the dispute data based on the data extract indicating the posted state.

Claims (38)

1 . A method for generating transaction dispute data, comprising:

detecting a deviation in transaction data;

in response to detecting a deviation, presenting a dispute request interface to a user via a graphical user interface on a user device, wherein the dispute request interface includes:

transaction data; and

an input area configured to receive input information, the input area including one or more interactive graphical user interface elements;

receiving dispute request input from the user device via the dispute request interface, wherein the dispute request input includes information relating to the disputed transaction;

presenting a dispute status to the user on the user device via the dispute request interface;

determining a dispute status update; and

presenting the dispute status update to the user on the user device via the dispute request interface.

2 . The method of claim 1 , wherein detecting the deviation in transaction data is between a transaction and a transaction pattern model, wherein:

the transaction pattern model is trained on user account data; and

the deviation is based on a difference between one or more data elements of the transaction and a corresponding parameter of the transaction pattern model.

3 . The method of claim 1 , wherein detecting the deviation in transaction data is between two or more transactions, wherein the two or more transactions have a threshold degree of similarity to each other.

4 . The method of claim 3 , wherein the threshold degree of similarity is based on each transaction having at least one of: a same transaction date, a same merchant, a same transaction payment method, or a same transaction amount.

5 . The method of claim 3 , wherein the threshold degree of similarity is based on each transaction having at least one of: a transaction date within a threshold number of days of each other, merchants operating in the same industry, merchant names having a threshold number of characters or words in common, or a transaction amount within a threshold amount of each other.

6 . The method of claim 1 , wherein user interface elements are configured to be displayed or interactable based on determining a particular dispute status update.

7 . The method of claim 6 , wherein user interface elements are configured to be displayed or interactable based on determining that the particular dispute status update has been indicated for a predetermined period of time.

8 . The method of claim 1 , wherein the dispute request interface is configured to activate a sensor of the user device.

9 . The method of claim 1 , wherein the information relating to the transaction includes any one or more of: a dispute reason, a transaction amount, an image, an item identifier, or an audio recording.

10 . The method of claim 1 , wherein the dispute status includes a visual indicator showing progress of a dispute.

11 . The method of claim 1 , wherein the dispute status update includes a visual indicator showing progress of a dispute.

12 . A system for generating transaction dispute data, the system comprising:

at least one processor; and

a non-transitory computer-readable medium containing a set of instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:

detecting a deviation in transaction data;

in response to detecting a deviation, presenting a dispute request interface to a user via a graphical user interface on a user device, wherein the dispute request interface includes:

transaction data; and

an input area configured to receive input information, the input area including one or more interactive graphical user interface elements;

receiving dispute request input from the user device via the dispute request interface, wherein the dispute request input includes information relating to the disputed transaction;

presenting a dispute status to the user on the user device via the dispute request interface;

determining a dispute status update; and

presenting the dispute status update to the user on the user device via the dispute request interface.

13 . The system of claim 12 , wherein detecting the deviation in transaction data is between a transaction and a transaction pattern model, wherein:

the transaction pattern model is trained on user account data; and

the deviation is based on a difference between one or more data elements of the transaction and a corresponding parameter of the transaction pattern model.

14 . The system of claim 12 , wherein detecting the deviation in transaction data is between two or more transactions, wherein the two or more transactions have a threshold degree of similarity to each other.

15 . The system of claim 12 , wherein user interface elements are configured to be displayed or interactable based on determining a particular dispute status update.

16 . The system of claim 12 , the information relating to the transaction includes any one or more of: a dispute reason, a transaction amount, an image, an item identifier, or an audio recording.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 7, 2024
From: KUBLER, JEFFREY PAUL; SAUNDERS, SHANE; SUTTHOFF, JOSEPH FREDRIC; LEUNG, JOE; MORRISON, LAUREN; PETERSEN, MATTHEW; RAYNAULT, DAVID; PONSARAN, PHILIP J.
To: FIDELITY INFORMATION SERVICES, LLC
Reel/Frame 067337/0299 →
Continuity (3)
Continuation 18194682 · Apr 3, 2023
Continuation 16904878 · Jun 18, 2020
Related Publication 20240265404A1 · Aug 8, 2024
References Cited (73)
US 7815106B1 · McConnell · 2010 [cited by examiner]
US 10223723B1 · Bodapati · 2019 [cited by examiner]
US 10379995B1 · Walters et al. · 2019 [cited by applicant]
US 10891631B2 · Ebel · 2021 [cited by examiner]
US 10915392B2 · Sylvester, II · 2021 [cited by examiner]
US 10958784B1 · Way · 2021 [cited by examiner]
US 11019090B1 · Smith et al. · 2021 [cited by applicant]
US 11195183B2 · Waters · 2021 [cited by examiner]
US 11321632B2 · Saleh · 2022 [cited by examiner]
US 11436206B2 · Daruna · 2022 [cited by examiner]
US 11823287B2 · Lowe · 2023 [cited by examiner]
US 11830044B2 · Benkreira · 2023 [cited by examiner]
US 11854004B2 · Walters · 2023 [cited by examiner]
US 11978049B1 · Bechar · 2024 [cited by examiner]
US 11995054B2 · Daruna · 2024 [cited by examiner]
US 12153552B1 · Mecca · 2024 [cited by examiner]
US 12393940B2 · Walters · 2025 [cited by examiner]
US 20060200407A1 · Hartley · 2006 [cited by examiner]
US 20130339237A1 · Rich et al. · 2013 [cited by applicant]
US 20140006275A1 · Hanson · 2014 [cited by examiner]
US 20150025995A1 · Yuan · 2015 [cited by examiner]
US 20150381405A1 · Male · 2015 [cited by examiner]
US 20160224958A1 · Unser et al. · 2016 [cited by applicant]
US 20160314111A1 · Fougner · 2016 [cited by applicant]
US 20170142222A1 · Libow et al. · 2017 [cited by applicant]
US 20180025071A1 · Ideses et al. · 2018 [cited by applicant]
US 20190114643A1 · Dewitt · 2019 [cited by examiner]
US 20190196899A1 · Sylvester, II · 2019 [cited by examiner]
US 20190205993A1 · Rodriguez · 2019 [cited by examiner]
US 20190279208A1 · Muller · 2019 [cited by examiner]
US 20200118230A1 · Woelfer · 2020 [cited by examiner]
US 20200151728A1 · Waters · 2020 [cited by examiner]
US 20200160232A1 · Saleh · 2020 [cited by examiner]
US 20200177966A1 · Kerkes · 2020 [cited by applicant]
US 20200184488A1 · Ebel · 2020 [cited by examiner]
US 20200250671A1 · Thomas · 2020 [cited by examiner]
US 20200265379A1 · Walker · 2020 [cited by examiner]
US 20200320534A1 · Yerradoddi · 2020 [cited by examiner]
US 20200380577A1 · Mossoba · 2020 [cited by examiner]
US 20210357923A1 · Walters · 2021 [cited by examiner]
US 20220051270A1 · Benkreira · 2022 [cited by examiner]
US 20220207006A1 · Daruna · 2022 [cited by examiner]
US 20220391720A1 · Dande · 2022 [cited by examiner]
US 20220391954A1 · Benkreira · 2022 [cited by examiner]
US 20220414074A1 · Daruna · 2022 [cited by examiner]
US 20230049335A1 · Lowe · 2023 [cited by examiner]
US 20230205744A1 · Olsen · 2023 [cited by examiner]
US 20230298016A1 · Osborn · 2023 [cited by examiner]
US 20240062235A1 · Whatley · 2024 [cited by examiner]
US 20240078545A1 · Walters · 2024 [cited by examiner]
US 20240087051A1 · Lowe · 2024 [cited by examiner]
US 20240220822A1 · Wellmann · 2024 [cited by examiner]
US 20240221009A1 · Wellmann · 2024 [cited by examiner]
US 20240249287A1 · Wieker · 2024 [cited by examiner]
US 20250014066A1 · Whatley · 2025 [cited by examiner]
US 20250284673A1 · Olsen · 2025 [cited by examiner]
CA 3165280A1 · 2021 [cited by examiner]
CN 111324740A · 2020 [cited by examiner]
CN 113228078A · 2021 [cited by examiner]
CN 120266139A · 2025 [cited by examiner]
CN 120476413A · 2025 [cited by examiner]
WO WO2010125577A1 · 2010 [cited by examiner]
WO WO2015009439A1 · 2015 [cited by examiner]
WO WO2020123560A1 · 2020 [cited by examiner]
WO WO2021150632A1 · 2021 [cited by examiner]
WO WO2022251238A1 · 2022 [cited by examiner]
WO WO2023048893A1 · 2023 [cited by examiner]
WO WO2024137998A1 · 2024 [cited by examiner]
WO WO2024144913A1 · 2024 [cited by examiner]
WO WO2024155860A2 · 2024 [cited by examiner]
Fidelity Bank (Fraud Alerts, retrieved from https://web.archive.org/web/20190124225041/https://www.fidelitybank.com/resources/security-center/fraud-alerts/, Wayback machine captured Jan. 24, 2019, examiner retrieved fro… [cited by examiner]
R. Chejkova-Nikolov et al., “Interoperability of bank statements: A case study,” 2015 38 [cited by applicant]
Y. Zhang et al., “The Impact of Artificial Intelligence and Blockchain on the Accounting Profession,” in IEEE Access, vol. 8, pp. 110461-110477, 2020, doi: 10.1109/Access.20203000505 (2020). [cited by applicant]