# US 2023/0057762 A1 · Predicting a time of an event associated with an instrument using a machine learning model

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

- Number: US 2023/0057762 A1
- Document ID: US20230057762A1
- Status: Published application
- Kind: A1
- Application number: 17/445,253
- Filed: 2021-08-17
- Published: 2023-02-23
- Earliest claimed: 2021-08-17
- Assignees: Capital One Services, LLC
- Applicants: Capital One Services, LLC
- Inventors: Abdelkader M'Hamed BENKREIRA; Joshua EDWARDS; Michael MOSSOBA
- Web page: https://patentgrep.com/patent/US20230057762A1

## CPC

- G06N 5/04: Inference or reasoning models
- G06N 3/08: Learning methods
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 20/00: Machine learning
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06Q 20/123: {Shopping for digital content}
- G06Q 20/4037: {Remote solvency checks}
- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- G06Q 40/02: Banking, e.g. interest calculation or account maintenance (credit or loans G06Q40/03)
- G06Q 20/0425: {the cheque being electronic only}
- 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

## Abstract

In some implementations, a device may receive information indicating that an instrument has been provided by a user to a recipient. The instrument may be associated with a value, and the instrument may be designated for the recipient. The device may determine, using the machine learning model, a prediction of a time of an event associated with the instrument based on the recipient. The event associated with the instrument may result in a reduction of a balance of an account of the user. The device may transmit to another device of the user, a notification indicating the prediction of the time of the event associated with the instrument.

## Claims

### Claim 1

A system for predicting a time of an event associated with an instrument using a machine learning model, the system comprising:
one or more memories; and
one or more processors, communicatively coupled to the one or more memories, configured to:
receive information indicating that the instrument has been provided by a user to a recipient,
wherein the instrument is associated with a value, and
wherein the instrument is designated for the recipient;
identify one or more characteristics associated with the recipient;
determine, using the machine learning model, a prediction of the time of the event associated with the instrument based on the one or more characteristics associated with the recipient;
determine, based on the prediction of the time and the value, whether a balance of an account of the user will reach a threshold as a result of the event associated with the instrument; and
transmit, to a device of the user, a notification based on a determination that the balance will reach the threshold as the result of the event associated with the instrument.

### Claim 2 (depends on 1)

The system of claim 1, wherein the information identifies one or more of: the recipient, the value, or a time when the instrument was provided by the user.

### Claim 3 (depends on 1)

The system of claim 1, wherein the one or more characteristics of the recipient used by the machine learning model to determine the prediction of the time include one or more of: a category associated with the recipient, demographic information associated with the recipient, or behavioral information associated with the recipient.

### Claim 4 (depends on 1)

The system of claim 1, wherein the one or more processors, to determine whether the balance of the account of the user will reach the threshold, are configured to:
determine an estimate of a future balance of the account of the user at the time; and
determine whether the balance of the account of the user will reach the threshold based on the estimate of the future balance of the account.

### Claim 5 (depends on 1)

The system of claim 1, wherein the machine learning model is trained to determine the prediction of the time based on historical data relating to time durations between provisions of instruments to recipients and respective events associated with the instruments.

### Claim 6 (depends on 5)

The system of claim 5, wherein the one or more processors are further configured to:
perform optical character recognition on instrument image data associated with the instruments to identify the historical data.

### Claim 7 (depends on 1)

The system of claim 1, wherein the one or more processors are further configured to one or more of:
cause a transfer of funds, based on the value, to increase the balance of the account, or
cause a hold on funds of the account based on the value.

### Claim 8 (depends on 1)

The system of claim 1, wherein the one or more processors, to identify the one or more characteristics of the recipient, are configured to:
perform natural language processing of a name of the recipient to identify the one or more characteristics.

### Claim 9

A method of predicting a time of an event associated with an instrument using a machine learning model, comprising:
receiving, by a device, information indicating that the instrument has been provided by a user to a recipient,
wherein the instrument is associated with a value, and
wherein the instrument is designated for the recipient;
determining, by the device, using the machine learning model, a prediction of the time of the event associated with the instrument based on the recipient,
wherein the event associated with the instrument will result in a reduction of a
balance of an account of the user; and
transmitting, by the device, to another device of the user, a notification indicating the prediction of the time of the event associated with the instrument.

### Claim 10 (depends on 9)

The method of claim 9, further comprising:
causing a transfer of funds, based on the value, to increase the balance of the account, or
causing a hold on funds of the account based on the value.

### Claim 11 (depends on 9)

The method of claim 9, wherein the machine learning model determines the prediction of the time based on a feature set that includes one or more of: a name of the recipient, a category associated with the recipient, demographic information associated with the recipient, behavioral information associated with the recipient, the value, or a transaction type associated with the instrument.

### Claim 12 (depends on 9)

The method of claim 9, wherein the prediction of the time is further based on a transit time estimate for the instrument based on a first location associated with the user and a second location associated with the recipient.

### Claim 13 (depends on 9)

The method of claim 9, wherein the event associated with the instrument is a cashing event or a depositing event.

### Claim 14 (depends on 9)

The method of claim 9, wherein the information includes an image of the instrument.

### Claim 15

A non-transitory computer-readable medium storing a set of instructions for predicting a time of an event associated with an instrument, the set of instructions comprising:
one or more instructions that, when executed by one or more processors of a device, cause the device to:
receive information indicating that the instrument has been provided by a user to a recipient,
wherein the instrument is associated with a value, and
wherein the instrument is designated for the recipient;
determine a prediction of the time of the event associated with the instrument based on the recipient,
wherein the event associated with the instrument will result in a reduction of a balance of an account of the user; and
perform one or more actions based on the prediction of the time of the event associated with the instrument.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the one or more instructions, that cause the device to perform the one or more actions, cause the device to:
transmit a notification to another device of the user,
cause a transfer of funds, based on the value, to increase the balance of the account, or
cause a hold on funds of the account based on the value.

### Claim 17 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the information includes an image of the instrument.

### Claim 18 (depends on 17)

The non-transitory computer-readable medium of claim 17, wherein the one or more instructions, when executed by the one or more processors, further cause the device to:
perform optical character recognition of the image to identify one or more of: the recipient, the value, an address of the user, or a date associated with provision of the instrument.

### Claim 19 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the one or more instructions, when executed by the one or more processors, further cause the device to:
determine, based on the prediction of the time and the value, whether the balance will reach a threshold as a result of the event associated with the instrument; and
transmit, to another device of the user, a notification based on a determination that the balance will reach the threshold as the result of the event associated with the instrument.

### Claim 20 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the prediction of the time is determined using a machine learning model trained to output the prediction based on an input of information associated with the recipient.
