# US 2024/0202822 A1 · Method and system for detection of anomalous rejections of foreign exchange requests

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

- Number: US 2024/0202822 A1
- Document ID: US20240202822A1
- Status: Published application
- Kind: A1
- Application number: 18/085,104
- Filed: 2022-12-20
- Published: 2024-06-20
- Earliest claimed: 2022-12-20
- Assignees: JPMorgan Chase Bank, N.A.
- Applicants: JPMorgan Chase Bank, N.A.
- Inventors: Nacho NAVARRO; Xiaomo LIU; Simran LAMBA; Akshat GUPTA; Sameena SHAH
- Web page: https://patentgrep.com/patent/US20240202822A1

## CPC

- G06Q 40/04: Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
- 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

## Abstract

A method and a system for detecting abnormal and/or anomalous rejections of requests for quotes for foreign exchange transactions are provided. The method includes: receiving a request for quote (RFQ) that relates to a proposed foreign exchange (FX) transaction; retrieving first information that relates to a financial capability of the requester to conduct the proposed FX transaction; applying a first algorithm that is designed to make an initial determination as to whether the RFQ is acceptable, based on the RFQ and the first information; when the initial determination indicates that the RFQ is not acceptable, applying a second algorithm that uses an artificial intelligence (AI) technique to determine a potential reason that the initial determination has indicated that the RFQ is not acceptable; and generating a report that includes information that relates to the potential reason that the initial determination has indicated that the RFQ is not acceptable.

## Claims

### Claim 1

A method for detecting anomalous rejections of requests for quotes for foreign exchange transactions, the method being implemented by at least one processor, the method comprising:
receiving, by the at least one processor from a first entity, a first request for quote (RFQ) that relates to a proposed foreign exchange (FX) transaction;
retrieving, by the at least one processor from a memory, first information that relates to a financial capability of the first entity to conduct the proposed FX transaction;
applying, by the at least one processor, a first algorithm that is designed to make an initial determination as to whether the first RFQ is acceptable, based on the first RFQ and the first information;
when the initial determination indicates that the first RFQ is not acceptable, applying, by the at least one processor, a second algorithm that uses an artificial intelligence (AI) technique to determine a potential reason that the initial determination has indicated that the first RFQ is not acceptable; and
generating a report that includes information that relates to the potential reason that the initial determination has indicated that the first RFQ is not acceptable.

### Claim 2 (depends on 1)

The method of claim 1, wherein the potential reason includes at least one from among a first reason that is based on an abnormal behavior of the first entity within a predetermined time interval, a second reason that is based on a product type that relates to the proposed FX transaction, a third reason that is based on a currency that relates to the proposed FX transaction, and a fourth reason that is based on a size of the proposed FX transaction.

### Claim 3 (depends on 2)

The method of claim 2, wherein the predetermined time interval includes one from among a 24-hour interval, a three-day interval, a seven-day interval, a 30-day interval, a six-month interval, and a twelve-month interval.

### Claim 4 (depends on 1)

The method of claim 1, wherein the second algorithm uses historical information that relates to previous transactions that have been conducted by the first entity as an input.

### Claim 5 (depends on 4)

The method of claim 4, wherein the second algorithm uses historical information that relates to previous transactions that have been conducted by a plurality of second entities that are similar to the first entity as an additional input.

### Claim 6 (depends on 5)

The method of claim 5, wherein the second algorithm uses historical information that relates to previous transactions that have been conducted by a plurality of third entities that are not similar to the first entity as another additional input.

### Claim 7 (depends on 6)

The method of claim 6, further comprising determining whether a particular entity is similar to the first entity by:
identifying a plurality of features that relates to the first entity;
identifying, for each respective entity from among a global set of entities, a corresponding set of features that relates to the respective entity;
determining, for each respective pairing of a respective entity with the first entity, a respective distance between the plurality of features that relates to the first entity and the corresponding set of features that relates to the respective entity; and
determining, for each respective pairing, whether the corresponding entity is similar to the first entity based on the determined distance.

### Claim 8 (depends on 7)

The method of claim 7, wherein each entity included in the global set of entities that is not determined as being similar to the first entity is determined as being included in the plurality of third entities.

### Claim 9 (depends on 1)

The method of claim 1, further comprising transmitting the report to a predetermined destination and displaying at least a portion of the report on a display via a graphical user interface (GUI).

### Claim 10

A computing apparatus for detecting anomalous rejections of requests for quotes for foreign exchange transactions, the computing apparatus comprising:
a processor;
a memory;
a display; and
a communication interface coupled to each of the processor, the memory, and the display,
wherein the processor is configured to:
receive, via the communication interface from a first entity, a first request for quote (RFQ) that relates to a proposed foreign exchange (FX) transaction;
retrieve, from the memory, first information that relates to a financial capability of the first entity to conduct the proposed FX transaction;
apply a first algorithm that is designed to make an initial determination as to whether the first RFQ is acceptable, based on the first RFQ and the first information;
when the initial determination indicates that the first RFQ is not acceptable, apply a second algorithm that uses an artificial intelligence (AI) technique to determine a potential reason that the initial determination has indicated that the first RFQ is not acceptable; and
generate a report that includes information that relates to the potential reason that the initial determination has indicated that the first RFQ is not acceptable.

### Claim 11 (depends on 10)

The computing apparatus of claim 10, wherein the potential reason includes at least one from among a first reason that is based on an abnormal behavior of the first entity within a predetermined time interval, a second reason that is based on a product type that relates to the proposed FX transaction, a third reason that is based on a currency that relates to the proposed FX transaction, and a fourth reason that is based on a size of the proposed FX transaction.

### Claim 12 (depends on 11)

The computing apparatus of claim 11, wherein the predetermined time interval includes one from among a 24-hour interval, a three-day interval, a seven-day interval, a 30-day interval, a six-month interval, and a twelve-month interval.

### Claim 13 (depends on 10)

The computing apparatus of claim 10, wherein the second algorithm uses historical information that relates to previous transactions that have been conducted by the first entity as an input.

### Claim 14 (depends on 13)

The computing apparatus of claim 13, wherein the second algorithm uses historical information that relates to previous transactions that have been conducted by a plurality of second entities that are similar to the first entity as an additional input.

### Claim 15 (depends on 14)

The computing apparatus of claim 14, wherein the second algorithm uses historical information that relates to previous transactions that have been conducted by a plurality of third entities that are not similar to the first entity as another additional input.

### Claim 16 (depends on 15)

The computing apparatus of claim 15, wherein the processor is further configured to determine whether a particular entity is similar to the first entity by:
identifying a plurality of features that relates to the first entity;
identifying, for each respective entity from among a global set of entities, a corresponding set of features that relates to the respective entity;
determining, for each respective pairing of a respective entity with the first entity, a respective distance between the plurality of features that relates to the first entity and the corresponding set of features that relates to the respective entity; and
determining, for each respective pairing, whether the corresponding entity is similar to the first entity based on the determined distance.

### Claim 17 (depends on 16)

The computing apparatus of claim 16, wherein each entity included in the global set of entities that is not determined as being similar to the first entity is determined as being included in the plurality of third entities.

### Claim 18 (depends on 10)

The computing apparatus of claim 10, wherein the processor is further configured to transmit, via the communication interface, the report to a predetermined destination and to cause the display to display at least a portion of the report via a graphical user interface (GUI).

### Claim 19

A non-transitory computer readable storage medium storing instructions for detecting anomalous rejections of requests for quotes for foreign exchange transactions, the storage medium comprising executable code which, when executed by a processor, causes the processor to:
receive, from a first entity, a first request for quote (RFQ) that relates to a proposed foreign exchange (FX) transaction;
retrieve, from a memory, first information that relates to a financial capability of the first entity to conduct the proposed FX transaction;
apply a first algorithm that is designed to make an initial determination as to whether the first RFQ is acceptable, based on the first RFQ and the first information;
when the initial determination indicates that the first RFQ is not acceptable, apply a second algorithm that uses an artificial intelligence (AI) technique to determine a potential reason that the initial determination has indicated that the first RFQ is not acceptable; and
generate a report that includes information that relates to the potential reason that the initial determination has indicated that the first RFQ is not acceptable.

### Claim 20 (depends on 19)

The storage medium of claim 19, wherein the potential reason includes at least one from among a first reason that is based on an abnormal behavior of the first entity within a predetermined time interval, a second reason that is based on a product type that relates to the proposed FX transaction, a third reason that is based on a currency that relates to the proposed FX transaction, and a fourth reason that is based on a size of the proposed FX transaction.
