# US 2023/0419314 A1 · Systems and methods for monitoring post-transaction adjustments

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0419314 A1
- Document ID: US20230419314A1
- Status: Published application
- Kind: A1
- Application number: 17/851,568
- Filed: 2022-06-28
- Published: 2023-12-28
- Earliest claimed: 2022-06-28
- Assignees: Capital One Services, LLC
- Applicants: Capital One Services, LLC
- Inventors: Anne Moshyedi; Allison Trager
- Web page: https://patentgrep.com/patent/US20230419314A1

## CPC

- G06Q 20/389: {Keeping log of transactions for guaranteeing non-repudiation of a transaction}
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/047: Probabilistic or stochastic networks
- G06N 3/0475: Generative networks
- G06N 3/094: Adversarial learning
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06N 20/20: Ensemble learning
- G06Q 20/4014: {Identity check for transactions}
- G06Q 20/4015: {using location information}
- G06Q 20/4016: {involving fraud or risk level assessment in transaction processing}
- G06Q 20/405: {Establishing or using transaction specific rules}
- G06Q 20/42: Confirmation, e.g. check or permission by the legal debtor of payment
- 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

## Abstract

Disclosed embodiments may include a system for monitoring post-transaction adjustments. The system may receive data associated with a transaction, and determine whether the transaction is indicative of a post-transaction event (PTE). The system may cause a user device to display, via a GUI, a notification to prompt a user to confirm the PTE occurred and to enter a post-transaction amount (PTA) associated with the PTE. The system may monitor the data to determine whether the data has been updated to include a second PTA, and if so, the system may determine whether the first and second PTAs match. When a match is determined, the system may confirm the transaction, modify the GUI to generate a modified GUI comprising a confirmation indication, and cause the user device to display the confirmation indication. When no match is determined, the system may initiate fraud prevention action(s).

## Claims

### Claim 1

A system comprising:
one or more processors; and
a memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, are configured to cause the system to:
receive data associated with a transaction conducted by a user;
determine, using a first machine learning model (MLM) and based on one or more factors, whether the transaction is indicative of a post-transaction event;
responsive to determining the transaction is indicative of the post-transaction event, cause a user device associated with the user to display a first notification, via a graphical user interface (GUI), to prompt the user to confirm that the post-transaction event occurred and to enter a first post-transaction amount associated with the post-transaction event;
receive, from the user via the GUI, a confirmation that the post-transaction event occurred and the first post-transaction amount;
monitor the data associated with the transaction to determine whether the data has been updated to include a second post-transaction amount;
responsive to determining the data has been updated to include the second post-transaction amount, determine whether the first and second post-transaction amounts match;
responsive to determining the first and second post-transaction amounts match:
confirm the transaction;
modify the GUI to generate a first modified GUI comprising a confirmation indication; and
cause the user device to display the confirmation indication; and
responsive to determining the first and second post-transaction amounts do not match, initiate one or more fraud prevention actions.

### Claim 2 (depends on 1)

The system of claim 1, wherein the one or more factors comprise transaction history, entity classification, entity type, geographic location, time of day, or combinations thereof.

### Claim 3 (depends on 1)

The system of claim 1, wherein the instructions are further configured to cause the system to:
responsive to determining the first and second post-transaction amounts do not match, cause the user device associated with the user to display a second notification, via the GUI, to request the user confirm the second post-transaction amount;
receive, from the user via the GUI, an indication that the second post-transaction amount is incorrect;
modify the GUI to generate a second modified GUI comprising an incorrect confirmation indication; and
cause the user device to display the incorrect confirmation indication associated with the first and second post-transaction amounts,
wherein initiating the one or more fraud prevention actions is based on receiving the indication.

### Claim 4 (depends on 1)

The system of claim 1, wherein the one or more fraud prevention actions comprise:
transmitting a second notification to an entity associated with the transaction; and
causing the user device associated with the user to display a third notification, via the GUI, to request whether the user would like to dispute the transaction.

### Claim 5 (depends on 4)

The system of claim 4, wherein the second notification is configured to enable the entity to adjust the second post-transaction amount.

### Claim 6 (depends on 4)

The system of claim 4, wherein the instructions are further configured to cause the system to:
receive a response to the third notification, the response indicating the user would like to dispute the transaction; and
responsive to receiving the response:
modify the GUI to generate a second modified GUI comprising a disputed indication; and
cause the user device to display the disputed indication.

### Claim 7 (depends on 1)

The system of claim 1, wherein the instructions are further configured to cause the system to:
determine, using a second MLM and based on the one or more factors, whether the first post-transaction amount exceeds a predetermined threshold; and
responsive to determining the first post-transaction amount exceeds the predetermined threshold, cause the user device associated with the user to display a second notification, via the GUI, indicating the first post-transaction amount may be higher than the user desires.

### Claim 8 (depends on 1)

The system of claim 1, wherein the instructions are further configured to cause the system to:
receive, from the user via the GUI, a request to monitor the transaction.

### Claim 9

A system comprising:
one or more processors; and
a memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, are configured to cause the system to:
receive data associated with a transaction conducted by a user;
determine, using a first machine learning model (MLM) and based on one or more factors, whether the transaction is indicative of a post-transaction event;
responsive to determining the transaction is indicative of the post-transaction event, cause a user device associated with the user to display a first notification, via a graphical user interface (GUI), to prompt the user to confirm the post-transaction event occurred;
receive, from the user via the GUI, a confirmation that the post-transaction event occurred;
responsive to receiving the confirmation that the post-transaction event occurred, determine, using a second MLM and based on the one or more factors, a first post-transaction amount associated with the post-transaction event;
monitor the data associated with the transaction to determine whether the data has been updated to include a second post-transaction amount;
responsive to determining the data has been updated to include the second post-transaction amount, determine whether the second post-transaction amount matches the first post-transaction amount within a predetermined threshold;
responsive to determining the second post-transaction amount matches the first post-transaction amount within the predetermined threshold:
confirm the transaction;
modify the GUI to generate a first modified GUI comprising a confirmation indication; and
cause the user device to display the confirmation indication; and
responsive to determining the second post-transaction amount does not match the first post-transaction amount within the predetermined threshold, cause the user device associated with the user to display a second notification, via the GUI, to prompt the user to confirm the second post-transaction amount.

### Claim 10 (depends on 9)

The system of claim 9, wherein the one or more factors comprise transaction history, entity classification, entity type, geographic location, time of day, or combinations thereof.

### Claim 11 (depends on 9)

The system of claim 9, wherein the predetermined threshold comprises a percentage range.

### Claim 12 (depends on 9)

The system of claim 9, wherein the instructions are further configured to cause the system to:
receive, from the user via the GUI, a first response to the second notification, the first response indicating the second post-transaction amount is incorrect;
modify the GUI to generate a second modified GUI comprising an incorrect confirmation indication;
cause the user device to display the incorrect confirmation indication associated with the first and second post-transaction amounts; and
responsive to receiving the first response, initiate one or more fraud prevention actions.

### Claim 13 (depends on 12)

The system of claim 12, wherein the one or more fraud prevention actions comprise:
transmitting a third notification to an entity associated with the transaction; and
causing the user device associated with the user to display a fourth notification, via the GUI, to request whether the user would like to dispute the transaction.

### Claim 14 (depends on 13)

The system of claim 13, wherein the third notification is configured to enable the entity to adjust the second post-transaction amount.

### Claim 15 (depends on 13)

The system of claim 13, wherein the instructions are further configured to cause the system to:
receive, from the user via the GUI, a second response to the fourth notification, the second response indicating the user would like to dispute the transaction; and
responsive to receiving the second response:
modify the GUI to generate a third modified GUI comprising a disputed indication; and
cause the user device to display the third modified GUI.

### Claim 16

A system comprising:
one or more processors; and
a memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, are configured to cause the system to:
receive data associated with a transaction conducted by a user;
determine, using a first machine learning model (MLM) and based on one or more factors, that the transaction is indicative of a post-transaction event;
responsive to determining the transaction is indicative of the post-transaction event, cause a user device associated with the user to display a first notification, via a graphical user interface (GUI), to prompt the user to confirm the post-transaction event occurred;
receive, from the user via the GUI, a confirmation that the post-transaction event occurred;
responsive to receiving the confirmation that the post-transaction event occurred, determine, using a second MLM and based on the one or more factors, a first post-transaction amount associated with the post-transaction event;
monitor the data associated with the transaction to determine whether the data has been updated to include a second post-transaction amount;
responsive to determining the data has been updated to include the second post-transaction amount, cause the user device associated with the user to display a second notification, via the GUI, to prompt the user to confirm the second post-transaction amount;
receive, from the user via the GUI, a first indication that the second post-transaction amount is correct;
responsive to receiving the first indication:
confirm the transaction;
modify the GUI to generate a first modified GUI comprising a confirmation indication; and
cause the user device to display the confirmation indication;
receive, from the user via the GUI, a second indication that the second post-transaction amount is incorrect; and
responsive to receiving the second indication, initiate one or more fraud prevention actions.

### Claim 17 (depends on 16)

The system of claim 16, wherein the one or more factors comprise transaction history, entity classification, entity type, geographic location, time of day, or combinations thereof.

### Claim 18 (depends on 16)

The system of claim 16, wherein the one or more fraud prevention actions comprise:
transmitting a third notification to an entity associated with the transaction; and
causing the user device associated with the user to display a fourth notification, via the GUI, to request whether the user would like to dispute the transaction.

### Claim 19 (depends on 18)

The system of claim 18, wherein the third notification is configured to enable the entity to adjust the second post-transaction amount.

### Claim 20 (depends on 18)

The system of claim 18, wherein the instructions are further configured to cause the system to:
receive, from the user via the GUI, a response to the fourth notification, the response indicating the user would like to dispute the transaction; and
responsive to receiving the response;
modify the GUI to generate a second modified GUI comprising a disputed indication; and
cause the user device to display the disputed indication.
