# US 2019/0378194 A1 · Systems and methods for adjusting transaction affinity information

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

- Number: US 2019/0378194 A1
- Document ID: US20190378194A1
- Status: Published application
- Kind: A1
- Application number: 16/006,711
- Filed: 2018-06-12
- Published: 2019-12-12
- Earliest claimed: 2018-06-12
- Assignees: Capital One Services, LLC
- Applicants: Capital One Services, LLC
- Inventors: Daniel Alan JARVIS; Lawrence Hutchison DOUGLAS, JR.; Jeffrey Carlyle Wieker
- Web page: https://patentgrep.com/patent/US20190378194A1

## CPC

- G06Q 30/0255: {based on user history}
- G06F 16/288: {Entity relationship models}
- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06F 16/9537: Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
- G06F 16/955: using information identifiers, e.g. uniform resource locators [URL]
- G06N 5/048: Fuzzy inferencing
- G06Q 30/0202: Market predictions or forecasting for commercial activities
- G06Q 30/0224: {based on user history}
- G06Q 30/0251: Targeted advertisements
- G06Q 30/0252: {based on events or environment, e.g. weather or festivals}
- G06Q 30/0631: {Recommending goods or services}
- 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)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

In certain aspects, the disclosed implementations include methods and systems for dynamically generating and providing transaction affinity recommendation data. In certain implementations, the transaction affinity recommendation data may include information that identifies a target merchant and associated merchant promotion data that may be generated based on a dynamic analysis of transaction data corresponding to an account record. In some aspects, the disclosed implementations may perform processes that determine adjustments to the merchant recommendation data based on one or more parameters associated with potential next merchants included in the merchant recommendation data. The disclosed implementations may analyze weigh values assigned to the one or more parameters, and based on the weight values and parameter information, may determine a different merchant is to be recommended. Based on the determination, the disclosed implementations may generate adjusted merchant recommendation data identifying a different recommended merchant.

## Claims

### Claim 1

A system for determining adjusted transaction affinity recommendation data, comprising:
transaction affinity platform computing components that execute software to perform operations that generate transaction affinity recommendation data; and
memory that stores the software and information used by the transaction affinity platform computing components to perform the operations to:
receive transaction data associated with a set of transactions associated with a first account record;
analyze the transaction data to generate a transaction affinity data set;
identify a first pair of temporally related transactions from the transaction affinity data set, the first pair of temporally related transactions including a first transaction and a second transaction that occurred later in time than the first transaction;
analyze transaction affinity data associated with each transaction in the first pair of temporally related transactions to determine time gap data associated with the first transaction and the second transaction;
generate trip transaction data based on the time gap data;
generate transaction affinity relationship data based on the trip transaction data;
generate, based on the transaction affinity relationship data, merchant recommendation data associated with a set of recommended merchants that have an affinity relationship with a target merchant, such that the merchant recommendation data is generated before a new transaction occurs after the second transaction and the merchant recommendation data identifies a first recommended merchant included in the set of recommended merchants;
determine merchant parameter information for each merchant in the set of recommended merchants;
receive input parameter information associated with a set of parameters that are included in the merchant parameter information;
determine a parameter weight value for each parameter in the set of parameters based on the input parameter information;
analyze the parameter weight values and the merchant parameter information;
determine an adjustment to the merchant recommendation data based on analyzing the parameter weight values and the merchant parameter information; and
generate, based on the determined adjustment, adjusted merchant recommendation data that identifies a second recommended merchant in the set of recommended merchants as an alternative to the first recommended merchant.

### Claim 2 (depends on 1)

The system of claim 1, wherein the merchant parameter information includes at least one of a distance parameter information reflecting a geographic distance between the target merchant and each merchant in the set of recommended merchants, incentive parameter information reflecting an indication of an incentive offered by each merchant in the set of recommended merchants, traffic parameter information reflecting a level of traffic between the target merchant and each merchant in the set of recommended merchants, and merchant rating parameter information reflecting a satisfaction rating level associated with each merchant in the set of recommended merchants,
the system further comprising that the transaction affinity platform computing components perform the operations to generate information used to provide an interface to receive the input parameter information, the input parameter information including at least one of a distance parameter priority value, an incentive parameter priority value, a traffic parameter priority value, and a merchant rating parameter priority value.

### Claim 3 (depends on 2)

The system of claim 2, further comprising that the transaction affinity platform computing components performs the operations that determines the parameter weight value for each parameter in the set of parameters based on the input parameter information by:
determining the parameter weight value for each parameter in the set of parameters based on at least one of the distance parameter priority value, an incentive parameter priority value, a traffic parameter priority value, and a merchant rating parameter priority value.

### Claim 4 (depends on 2)

The system of claim 2, further comprising that the transaction affinity platform computing components performs the operations that determine the adjustment to the merchant recommendation data by:
determining a current time information when the first recommended merchant is determined;
determining that the merchant parameter information for the first recommended merchant reflects that the first recommended merchant is unavailable based on the current time information;
analyzing the merchant parameter information for a potential recommended merchant in the set of recommended merchants to determine that the potential recommended merchant is available based on the current time information; and
identifying, based on analyzing the merchant parameter information, the potential recommended merchant as the second recommended merchant.

### Claim 5 (depends on 1)

The system of claim 1, wherein the set of recommended merchants includes a first potential recommended merchant, and the parameter information associated with the first recommended merchant includes a distance parameter value that reflects a first distance between the target merchant and the first recommended merchant, and wherein the parameter information associated with the first potential recommended merchant includes a distance parameter value that reflects a second distance between the target merchant and the first potential recommended merchant, and wherein the transaction affinity platform computing components perform the operations that determine the adjustment to the merchant recommendation data by:
analyzing the distance parameter value associated with the first potential recommended merchant and the distance parameter value associated with the first recommended merchant, and
identifying the first potential recommended merchant as the second recommended merchant based on the analysis.

### Claim 6 (depends on 1)

The system of claim 1, further comprising that the transaction affinity platform computing components performs the operations to determine an adjustment to the merchant recommendation data based on analyzing the parameter weight values and the merchant parameter information by:
analyzing merchant parameter information associated with the merchants in the set of recommended merchants to determine that a potential recommended merchant in the set of recommended merchants is a merchant partner; and
identifying the potential recommended merchant as the second recommended merchant based on the determination that the potential recommended merchant is identified as a merchant partner.

### Claim 7 (depends on 1)

The system of claim 1, further comprising that the transaction affinity platform computing components performs the operations to determine an adjustment to the merchant recommendation data based on analyzing the parameter weight values and the merchant parameter information by:
analyzing merchant parameter information associated with the merchants in the set of recommended merchants to determine that a potential recommended merchant in the set of recommended merchants is a merchant partner associated with the first account record; and
identifying the potential recommended merchant as the second recommended merchant based on the determination that the potential recommended merchant is identified as a merchant partner associated with the first account record.

### Claim 8 (depends on 1)

The system of claim 1, further comprising that the transaction affinity platform computing components performs the operations to:
generate the second merchant recommendation data to include a merchant identifier for the second recommended merchant, parameter information associated with the second recommended merchant, and recommendation message data reflecting information that conveys a recommendation of the second recommendation merchant; and
provide the second merchant recommendation data to a computing device for display in an interface of a display device.

### Claim 9

A method for determining adjusted transaction affinity recommendation data performed by transaction affinity platform computing components that execute software stored in a memory, the method comprising:
receiving transaction data associated with a set of transactions associated with a first account record;
analyzing the transaction data to generate a transaction affinity data set;
identifying a first pair of temporally related transactions from the transaction affinity data set, the first pair of temporally related transactions including a first transaction and a second transaction that occurred later in time than the first transaction;
analyzing transaction affinity data associated with each transaction in the first pair of temporally related transactions to determine time gap data associated with the first transaction and the second transaction;
generating trip transaction data based on the time gap data;
generating transaction affinity relationship data based on the trip transaction data;
generating, based on the transaction affinity relationship data, merchant recommendation data associated with a set of recommended merchants that have an affinity relationship with a target merchant, such that the merchant recommendation data is generated before a new transaction occurs after the second transaction and the merchant recommendation data identifies a first recommended merchant included in the set of recommended merchants;
determining merchant parameter information for each merchant in the set of recommended merchants;
receiving input parameter information associated with a set of parameters, the set of parameters associated with parameters included in the merchant parameter information;
determining a parameter weight value for each parameter in the set of parameters based on the input parameter information;
analyzing the parameter weight values and the merchant parameter information;
determining an adjustment to the merchant recommendation data based on analyzing the parameter weight values and the merchant parameter information; and
generating, based on the determined adjustment, adjusted merchant recommendation data that identifies a second recommended merchant in the set of recommended merchants in place of the first recommended merchant.

### Claim 10 (depends on 9)

The method of claim 9, wherein the merchant parameter information includes at least one of a distance parameter information reflecting a geographic distance between the target merchant and each merchant in the set of recommended merchants, incentive parameter information reflecting an indication of an incentive offered by each merchant in the set of recommended merchants, traffic parameter information reflecting a level of traffic between the target merchant and each merchant in the set of recommended merchants, and merchant rating parameter information reflecting a satisfaction rating level associated with each merchant in the set of recommended merchants, the method further comprising:
generating information used to provide an interface to receive the input parameter information, the input parameter information including at least one of a distance parameter priority value, an incentive parameter priority value, a traffic parameter priority value, and a merchant rating parameter priority value.

### Claim 11 (depends on 10)

The method of claim 10, further comprising:
determining the parameter weight value for each parameter in the set of parameters based on at least one of the distance parameter priority value, an incentive parameter priority value, a traffic parameter priority value, and a merchant rating parameter priority value.

### Claim 12 (depends on 10)

The method of claim 10, further comprising:
determining a current time information when the first recommended merchant is determined;
determining that the merchant parameter information for the first recommended merchant reflects that the first recommended merchant is unavailable based on the current time information;
analyzing the merchant parameter information for a potential recommended merchant in the set of recommended merchants to determine that the potential recommended merchant is available based on the current time information; and
identifying, based on analyzing the merchant parameter information, the potential recommended merchant as the second recommended merchant.

### Claim 13 (depends on 9)

The method of claim 9, wherein the set of recommended merchants includes a first potential recommended merchant, and the parameter information associated with the first recommended merchant includes a distance parameter value that reflects a first distance between the target merchant and the first recommended merchant, and the parameter information associated with the first potential recommended merchant includes a distance parameter value that reflects a second distance between the target merchant and the first potential recommended merchant, the method further comprising:
analyzing the distance parameter value associated with the first potential recommended merchant and the distance parameter value associated with the first recommended merchant; and
identifying the first potential recommended merchant as the second recommended merchant based on the analysis.

### Claim 14 (depends on 9)

The method of claim 9, wherein determining the adjustment to the merchant recommendation data based on analyzing the parameter weight values and the merchant parameter information includes:
analyzing merchant parameter information associated with the merchants in the set of recommended merchants to determine that a potential recommended merchant in the set of recommended merchants is a merchant partner; and
identifying the potential recommended merchant as the second recommended merchant based on the determination that the potential recommended merchant is identified as a merchant partner.

### Claim 15 (depends on 9)

The method of claim 9, wherein determining the adjustment to the merchant recommendation data based on analyzing the parameter weight values and the merchant parameter information includes:
analyzing merchant parameter information associated with the merchants in the set of recommended merchants to determine that a potential recommended merchant in the set of recommended merchants is a merchant partner associated with the first account record; and
identifying the potential recommended merchant as the second recommended merchant based on the determination that the potential recommended merchant is identified as a merchant partner associated with the first account record.

### Claim 16 (depends on 9)

The method of claim 9, further comprising:
generating the second merchant recommendation data to include a merchant identifier for the second recommended merchant, parameter information associated with the second recommended merchant, and recommendation message data reflecting information that conveys a recommendation of the second recommendation merchant; and
providing the second merchant recommendation data to a computing device for display in an interface of a display device.

### Claim 17

A non-transitory computer-readable medium storing instructions for wireless communication, the instructions comprising:
one or more instructions that, when executed by one or more processors, cause the one or more processors to:
receive transaction data associated with a set of transactions associated with a first account record;
analyze the transaction data to generate a transaction affinity data set;
identify a first pair of temporally related transactions from the transaction affinity data set, the first pair of temporally related transactions including a first transaction and a second transaction that occurred later in time than the first transaction;
analyze transaction affinity data associated with each transaction in the first pair of temporally related transactions to determine time gap data associated with the first transaction and the second transaction;
generate trip transaction data based on the time gap data;
generate transaction affinity relationship data based on the trip transaction data;
generate, based on the transaction affinity relationship data, merchant recommendation data associated with a set of recommended merchants that have an affinity relationship with a target merchant, such that the merchant recommendation data is generated before a new transaction occurs after the second transaction and the merchant recommendation data identifies a first recommended merchant included in the set of recommended merchants;
determine merchant parameter information for each merchant in the set of recommended merchants;
receive input parameter information associated with a set of parameters, the set of parameters associated with parameters included in the merchant parameter information;
determine a parameter weight value for each parameter in the set of parameters based on the input parameter information;
analyze the parameter weight values and the merchant parameter information;
determine an adjustment to the merchant recommendation data based on analyzing the parameter weight values and the merchant parameter information; and
generate, based on the determined adjustment, adjusted merchant recommendation data that identifies a second recommended merchant in the set of recommended merchants in place of the first recommended merchant.

### Claim 18 (depends on 17)

The non-transitory computer-readable medium of claim 17, wherein the merchant parameter information includes at least one of a distance parameter information reflecting a geographic distance between the target merchant and each merchant in the set of recommended merchants, incentive parameter information reflecting an indication of an incentive offered by each merchant in the set of recommended merchants, traffic parameter information reflecting a level of traffic between the target merchant and each merchant in the set of recommended merchants, and merchant rating parameter information reflecting a satisfaction rating level associated with each merchant in the set of recommended merchants, the one or more instructions further causing the one or more processors to:
generate information used to provide an interface to receive the input parameter information, the input parameter information including at least one of a distance parameter priority value, an incentive parameter priority value, a traffic parameter priority value, and a merchant rating parameter priority value.

### Claim 19 (depends on 18)

The non-transitory computer-readable medium of claim 18, wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
determine the parameter weight value for each parameter in the set of parameters based on at least one of the distance parameter priority value, an incentive parameter priority value, a traffic parameter priority value, and a merchant rating parameter priority value.

### Claim 20 (depends on 18)

The non-transitory computer-readable medium of claim 18, wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
determine a current time information when the first recommended merchant is determined;
determine that the merchant parameter information for the first recommended merchant reflects that the first recommended merchant is unavailable based on the current time information;
analyze the merchant parameter information for a potential recommended merchant in the set of recommended merchants to determine that the potential recommended merchant is available based on the current time information; and
identify, based on analyzing the merchant parameter information, the potential recommended merchant as the second recommended merchant.
