# US 12,002,086 B2 · Visualizing interest charges based on payment options

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

- Number: US 12,002,086 B2
- Document ID: US12002086B2
- Status: Granted
- Kind: B2
- Application number: 18/061,696
- Filed: 2022-12-05
- Published: 2023-03-30
- Granted: 2024-06-04
- Earliest claimed: 2020-05-14
- Assignees: Capital One Services, LLC
- Applicants: Capital One Services, LLC
- Inventors: Afna Kanhirothan Polil; Eric K. Barnum; Seshu Pitcha
- Web page: https://patentgrep.com/patent/US12002086B2

## CPC

- G06Q 40/02: Banking, e.g. interest calculation or account maintenance (credit or loans G06Q40/03)
- G06N 5/04: Inference or reasoning models
- G06N 20/00: Machine learning
- G06Q 10/04: Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202)
- G06Q 10/109: Time management, e.g. calendars, reminders, meetings or time accounting
- G06Q 20/102: {Bill distribution or payments}
- G06Q 20/108: {Remote banking, e.g. home banking}
- G06Q 20/14: specially adapted for billing systems
- G06Q 20/227: {characterised in that multiple accounts are available, e.g. to the payer}
- G06Q 20/3221: {Access to banking information through M-devices}
- G06Q 20/40: Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06F 3/04847: Interaction techniques to control parameter settings, e.g. interaction with sliders or dials
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

Systems as described herein may visualization interest charges based on payment options. Transaction information associated with a plurality of recurring payment accounts may be received. A calendar view displaying an aggregated daily balance and an aggregated interest charge may be generated. Upon receiving a transaction request with a transaction amount, a projected aggregated daily interest charge may be generated in real-time. After detecting that the projected aggregated daily interest charge exceeds a threshold amount, an alert associated with the calendar view may be generated to recommend an alternative payment method to a user device.

## Claims

### Claim 1

A computer-implemented method comprising:
receiving, by an electronic payment system, transaction information that is associated with a plurality of recurring payment accounts for a user;
training a machine learning classifier to determine an optimal threshold amount for the plurality of recurring payment accounts associated with the user, by:
assigning, by the machine learning classifier, an initial threshold amount indicating a preferred threshold received from the user;
generating, based on the initial threshold amount, one or more alerts associated with a historical calendar view, wherein the historical calendar view displays an aggregated daily balance associated with each of a plurality of historical dates, and an aggregated daily interest charge associated with each of the plurality of historical dates;
receiving, from a user device, user correction action in response to the one or more alerts; and
iteratively adjusting, by the machine learning classifier and based on the user corrective action, the initial threshold amount to generate the optimal threshold amount;
detecting, by the electronic payment system, that a projected aggregated daily interest charge exceeds the optimal threshold amount, wherein the projected aggregated daily interest charge is based on a calendar view of the transaction information of the plurality of recurring payment accounts; and
after detecting that the projected aggregated daily interest charge exceeds the optimal threshold amount, sending, by the electronic payment system to the user device, an alert recommending an alternative payment method.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the alternative payment method comprises at least one of: a cash payment, a payment via a debit card, or a checking account.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein the training the machine learning classifier comprises training the machine learning classifier using a set of training data comprising frequencies and sizes of historical payments made by the user.

### Claim 4 (depends on 1)

The method of claim 1, wherein training the machine learning classifier to determine the optimal threshold amount comprises:
training, using training data comprising historical payment data associated with a plurality of users, the machine learning classifier to output recommended payment thresholds;
providing, as input to the trained machine learning classifier, payment information associated with the user; and
receiving, as output from the trained machine learning classifier and based on the payment information, the optimal threshold amount.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, further comprising:
generating, by the electronic payment system, the calendar view associated with the plurality of recurring payment accounts, wherein the calendar view displays an aggregated daily balance associated with each of a plurality of dates, and the aggregated daily interest charge associated with each of the plurality of dates.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, further comprising:
receiving, from the user, a first projected payment amount to be allocated to a first recurring payment account of the plurality of recurring payment accounts; and
based on the first projected payment amount, generating, by the electronic payment system, a first projected calendar view and a first projected payoff end date.

### Claim 7 (depends on 6)

The computer-implemented method of claim 6, further comprising:
receiving, from the user, a second projected payment amount to be allocated to a second recurring payment account of the plurality of recurring payment accounts; and
based on the second projected payment amount, generating, by the electronic payment system, a second projected calendar view and a second projected payoff date.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, further comprising:
detecting, by the electronic payment system and based on the transaction information, a payment pattern associated with the user corresponding to the plurality of recurring payment accounts; and
determining an optimal payment schedule based on the payment pattern to minimize an aggregated interest payment amount on the plurality of recurring payment accounts.

### Claim 9 (depends on 8)

The computer-implemented method of claim 8, wherein the payment pattern comprises amounts and frequencies of payments associated with the plurality of recurring payment accounts.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1, wherein the plurality of recurring payment accounts comprise at least one of: a credit card account, a car loan account and a mortgage account.

### Claim 11

An electronic payment system comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the electronic payment system to:
receive transaction information that is associated with a plurality of recurring payment accounts for a user;
train a machine learning classifier to determine an optimal threshold amount for the plurality of recurring payment accounts associated with the user by:
assigning, by the machine learning classifier, an initial threshold amount indicating a preferred threshold received from the user;
generating, based on the initial threshold amount, one or more alerts associated with a historical calendar view, wherein the historical calendar view displays an aggregated daily balance associated with each of a plurality of historical dates, and an aggregated daily interest charge associated with each of the plurality of historical dates;
receiving, from a user device, user correction action in response to the one or more alerts; and
iteratively adjusting, by the machine learning classifier and based on the user corrective action, the initial threshold amount to generate the optimal threshold amount;
detect that a projected daily interest charge exceeds the optimal threshold amount, wherein the projected daily interest charge is based on a calendar view of the transaction information of the plurality of recurring payment accounts; and
after detecting that the projected daily interest charge exceeds the optimal threshold amount, send, to the user device, an alert recommending an alternative payment method.

### Claim 12 (depends on 11)

The electronic payment system of claim 11, wherein the alternative payment method comprises at least one of: a cash payment, a payment via a debit card, or a checking account.

### Claim 13 (depends on 11)

The electronic payment system of claim 11, wherein the instructions, when executed by the one or more processors, cause the electronic payment system to:
train the machine learning classifier using a set of training data comprising frequencies and sizes of historical payments made by the user.

### Claim 14 (depends on 11)

The electronic payment system of claim 11, wherein the instructions, when executed by the one or more processors, cause the electronic payment system to:
train, using training data comprising historical payment data associated with a plurality of users, the machine learning classifier to output recommended payment thresholds;
provide, as input to the trained machine learning classifier, payment information associated with the user; and
receive, as output from the trained machine learning classifier and based on the payment information, the optimal threshold amount.

### Claim 15 (depends on 11)

The electronic payment system of claim 11, wherein the instructions, when executed by the one or more processors, cause the electronic payment system to:
generate the calendar view associated with the plurality of recurring payment accounts, wherein the calendar view displays an aggregated daily balance associated with each of a plurality of dates, and the aggregated daily interest charge associated with each of the plurality of dates.

### Claim 16 (depends on 13)

The electronic payment system of claim 13, wherein the instructions, when executed by the one or more processors, cause the electronic payment system to:
receive, from the user, a first projected payment amount to be allocated to the recurring payment account; and
based on the first projected payment amount, generate a first projected calendar view and a first projected payoff end date.

### Claim 17 (depends on 11)

The electronic payment system of claim 11, wherein the instructions, when executed by the one or more processors, cause the electronic payment system to:
generate guidance associated with a payment schedule, wherein the guidance comprises information on promotional offers, balance transfers or refinancing opportunities.

### Claim 18

One or more non-transitory media storing instructions that, when executed by one or more processors, cause the one or more processors to perform steps comprising:
receiving transaction information that is associated with a plurality of recurring payment accounts for a user;
training a machine learning classifier to determine an optimal threshold amount for the plurality of recurring payment accounts associated with the user by:
assigning, by the machine learning classifier, an initial threshold amount indicating a preferred threshold received from the user;
generating, based on the initial threshold amount, one or more alerts associated with a historical calendar view, wherein the historical calendar view displays an aggregated daily balance associated with each of a plurality of historical dates, and an aggregated daily interest charge associated with each of the plurality of historical dates;
receiving, from a user device, user correction action in response to the one or more alerts; and
iteratively adjusting, by the machine learning classifier and based on the user corrective action, the initial threshold amount to generate the optimal threshold amount;
detecting that a projected aggregated daily interest charge exceeds the optimal threshold amount, wherein the projected aggregated daily interest charge is based on a calendar view of the transaction information of the plurality of recurring payment accounts; and
after detecting that the projected aggregated daily interest charge exceeds the optimal threshold amount, sending, to the user device, an alert recommending an alternative payment method.

### Claim 19 (depends on 18)

The non-transitory media of claim 18, wherein the instructions, when executed by the one or more processors, cause the one or more processors to perform further steps comprising:
detecting, based on the transaction information, a payment pattern associated with the user corresponding to the plurality of recurring payment accounts; and
determining an optimal payment schedule based on the payment pattern to minimize an aggregated interest payment amount on the plurality of recurring payment accounts.

### Claim 20 (depends on 18)

The non-transitory media of claim 18, wherein the instructions, when executed by the one or more processors, cause the one or more processors to perform further steps comprising:
training, using training data comprising historical payment data associated with a plurality of users, the machine learning classifier to output recommended payment thresholds;
providing, as input to the trained machine learning classifier, payment information associated with the user; and
receiving, as output from the trained machine learning classifier and based on the payment information, the optimal threshold amount.