# US 2023/0401578 A1 · Automatic modification of transaction constraints

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

- Number: US 2023/0401578 A1
- Document ID: US20230401578A1
- Status: Published application
- Kind: A1
- Application number: 17/837,188
- Filed: 2022-06-10
- Published: 2023-12-14
- Earliest claimed: 2022-06-10
- Assignees: Oracle International Corporation; Oracle Financial Services Software Limited
- Applicants: Oracle Financial Services Software Limited
- Inventors: Govind Gopinathan NAIR; Mohini SHRIVASTAVA; Saurabh ARORA; Jason P. SOMRAK
- Web page: https://patentgrep.com/patent/US20230401578A1

## CPC

- G06N 3/092: Reinforcement learning
- G06Q 20/401: {Transaction verification}
- G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques}
- G06N 20/00: Machine learning
- G06Q 20/4016: {involving fraud or risk level assessment in transaction processing}
- G06Q 20/405: {Establishing or using transaction specific rules}
- G06Q 40/02: Banking, e.g. interest calculation or account maintenance (credit or loans G06Q40/03)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Systems, methods, and other embodiments associated with automatic transaction constraint modification are described herein. In one embodiment, a method includes recording transactions by a reinforcement learning agent during attempts to evade one or more scenarios of a monitoring system. A usage frequency is determined for a product in a subset of the attempts to evade the one or more scenarios that are successful. The usage frequency is then compared to an expected usage frequency for the product. A transaction constraint on the product is then automatically modified to cause the usage frequency to be at or below the expected usage frequency.

## Claims

### Claim 1

A computer-implemented method, comprising:
recording transactions by a reinforcement learning agent during attempts to evade one or more scenarios of a monitoring system;
determining a usage frequency for a product in a subset of the attempts to evade the one or more scenarios that are successful;
comparing the usage frequency to an expected usage frequency for the product; and
automatically modifying a transaction constraint on the product to cause the usage frequency to be at or below the expected usage frequency.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the modifying the transaction constraint further comprises:
iteratively
(i) generating a tightened transaction constraint on the product,
(ii) determining an additional usage frequency for the tightened transaction constraint, and
(iii) comparing the additional usage frequency to the expected usage frequency,
until the additional usage frequency is at or below the expected usage frequency; and
modifying the transaction constraint to match the tightened transaction constraint.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein the comparing the usage frequency to the expected usage frequency further comprises:
determining an extent to which the usage frequency exceeds the expected usage frequency; and
comparing the extent to a pre-selected threshold, wherein the modifying the transaction constraint on the product is performed in response to the extent satisfying the pre-selected threshold.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein the modifying the transaction constraint on the product further comprises instructing the monitoring system to apply the modified transaction constraint to live transactions or live accounts in a monitored system that is monitored by the monitoring system.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein the modifying the transaction constraint on the product further comprises instructing the monitoring system to apply the modified transaction constraint to live transactions or live accounts associated with a first customer segment, and to not apply the modified transaction constraint to live transactions or live accounts associated with a second customer segment.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, further comprising:
determining a new usage frequency for the product following the modification of the transaction constraint;
presenting the new usage frequency for the product in a user interface;
presenting in the user interface a user-selectable element to accept the modifying the transaction constraint; and
accepting in the user interface a user selection of the element to accept the modifying, wherein the modifying the transaction constraint is performed in response to the user selection.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein the product is a type of transaction channel through which amounts may be transferred from one account to another account, wherein the modifying the transaction constraint further comprises reducing a size of amount permitted to be transferred through the transaction channel in a single transaction.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein the product is a type of account into which amounts may be transferred and from which the amounts may be retrieved, wherein the modifying the transaction constraint further comprises reducing a size of amount permitted to be transferred (i) into the type of account in a single transaction or (ii) out of the type of account in a single transaction.

### Claim 9

A computing system comprising:
a processor;
a memory operably connected to the processor;
a non-transitory computer-readable medium operably connected to the processor and memory and storing computer-executable instructions that when executed by at least a processor of the computing system cause the computing system to:
record transactions by a reinforcement learning agent during attempts to evade one or more scenarios of a monitoring system;
determine a usage frequency for a product in a subset of the attempts to evade the one or more scenarios that are successful;
compare the usage frequency to an expected usage frequency for the product; and
automatically modify a transaction constraint on the product to cause the usage frequency to be at or below the expected usage frequency.

### Claim 10 (depends on 9)

The computing system of claim 9, wherein the instructions to automatically modify the transaction constraint further cause the computing system to:
iteratively
(i) generating a tightened transaction constraint on the product,
(ii) determining an additional usage frequency for the tightened transaction constraint, and
(iii) comparing the additional usage frequency to the expected usage frequency,
until the additional usage frequency is at or below the expected usage frequency; and
modify the transaction constraint to match the tightened transaction constraint.

### Claim 11 (depends on 9)

The computing system of claim 9, wherein the instructions to compare the usage frequency to the expected usage frequency further cause the computing system to:
determine an extent to which the usage frequency exceeds the expected usage frequency; and
compare the extent to a pre-selected threshold, wherein the modifying the transaction constraint on the product is performed in response to the extent satisfying the pre-selected threshold.

### Claim 12 (depends on 9)

The computing system of claim 9, wherein the instructions to automatically modify the transaction constraint on the product further cause the computing system to instruct the monitoring system to apply the modified transaction constraint to live transactions or live accounts in a monitored system that is monitored by the monitoring system.

### Claim 13 (depends on 9)

The computing system of claim 9, wherein the instructions further cause the computing system to:
presenting in a user interface a user-selectable element to accept the modifying the transaction constraint; and
accepting in the user interface a user selection of the element to accept the modifying, wherein the modifying the transaction constraint is performed in response to the user selection.

### Claim 14 (depends on 9)

The computing system of claim 9, wherein the instructions to automatically modify the transaction constraint further causes the computing system to one of (i) reduce a size of amount permitted to be transferred through a type of transaction channel; or (ii) reduce a size of amount permitted to be transferred into or out of a type of account.

### Claim 15

A non-transitory computer-readable medium having stored thereon computer-executable instructions that, when executed by a processor accessing memory of a computer cause the computer to:
record transactions by a reinforcement learning agent during attempts to evade one or more scenarios of a monitoring system;
determine a usage frequency for a product in a subset of the attempts to evade the one or more scenarios that are successful;
compare the usage frequency to an expected usage frequency for the product; and
automatically modify a transaction constraint on the product to cause the usage frequency to be at or below the expected usage frequency.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the instructions to automatically modify the transaction constraint further cause the computer to:
iteratively
(i) generating a tightened transaction constraint on the product,
(ii) determining an additional usage frequency for the tightened transaction constraint, and
(iii) comparing the additional usage frequency to the expected usage frequency,
until the additional usage frequency is at or below the expected usage frequency; and
modifying the transaction constraint to match the tightened transaction constraint.

### Claim 17 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the instructions to compare the usage frequency to the expected usage frequency further cause the computer to:
determine an extent to which the usage frequency exceeds the expected usage frequency; and
compare the extent to a pre-selected threshold, wherein the modifying the transaction constraint on the product is performed in response to the extent satisfying the pre-selected threshold.

### Claim 18 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the instructions to automatically modify the transaction constraint on the product further cause the computer to instruct the monitoring system to apply the modified transaction constraint to live transactions or live accounts in a monitored system that is monitored by the monitoring system.

### Claim 19 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the instructions further cause the computer to:
presenting in a user interface a user-selectable element to accept the modifying the transaction constraint; and
accepting in the user interface a user selection of the element to accept the modifying, wherein the modifying the transaction constraint is performed in response to the user selection.

### Claim 20 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the instructions to automatically modify the transaction constraint further causes the computer to one of (i) reduce a size of cumulative amount permitted to be transferred through a type of transaction channel in a period of time; or (ii) reduce a size of cumulative amount permitted to be transferred into or out of a type of account in a period of time.
