Method and system to predict ATM locations for users

Patent metadata

Field	Value
Publication number	US-11037115-B2
Application number	US-201916568848-A
Country	US
Kind code	B2
Filing date	Sep 12, 2019
Priority date	Sep 12, 2019
Publication date	Jun 15, 2021
Grant date	Jun 15, 2021

Abstract

A system and method for routing customers to an automated teller machine (ATM) is disclosed herein. A computing system receives, from a client device, a request to locate an ATM. The request includes a constraint of a desired ATM. The computing system identifies a plurality of ATMs proximate a location of the client device. The computing system pings the plurality of ATMs proximate the location of the client device to identify attributes associated with each respective ATM. The computing system receives the attributes from the plurality of ATMs proximate the location of the client device. The computing system compares the attributes from each respective ATM to historical ATM usage statistics associated with the client device. The computing system routes a user of the client device to a target ATM from the plurality of ATMs based at least partially on the historical ATM usage statistics.

First claim

What is claimed:

1. A method of routing customers to an automated teller machine (ATM), comprising:
retrieving, by a computing system associated with at least one financial institution having an ATM network, historical ATM transaction data for a plurality of users of the ATM network, wherein the historical ATM transaction data comprises, for each individual user, a user identifier and attributes of a respective ATM associated with each historical ATM transaction executed by that user;
training, by the computing system using a machine learning module of the computing system, a plurality of prediction models, to learn individualized user ATM habits based on training sets comprising the historical ATM transaction data for each user;
storing in a database associated with the computing system, for each user, the user identifier, the historical ATM transaction data for the user and a respective prediction model for predicting the individualized ATM habits of the user and the attributes of the ATMs the user frequents, wherein the user's ATMs comprise ATMs associated with the financial institution and third party ATMs;
receiving, by the computing system from a client device associated with a user, a request to locate a target ATM, wherein the request comprises a constraint of a desired ATM, wherein the computing system is in electronic communication with an application installed on the client device for providing location services and electronic dialog messaging services to the computing system, wherein the request is generated by the user using an interface generated on the client device by the application;

determining, by the computing system and based on the request, the user identifier associated with the user and a location of the client device;
accessing, from the database and based on the determined user identifier, the prediction model associated with the user;
identifying, by the computing system, a plurality of ATMs proximate the location of the client device based on the constraint, wherein the plurality of identified ATMs are selected from a group comprising financial institution ATMs and third party ATMs;
generating, by the computing system via the user's individual prediction model, a personalized ATM recommendation for the user by:
prompting, via the interface on the client device, the user to enter parameters associated with the user's desired transaction;
identifying, by the computing system, based on the user's entered parameters, current attributes associated with each respective ATM of the plurality of ATMs
proximate to the location of the client device, wherein the computing system, in response to the request, communicates with each respective ATM to identify current attributes; and
comparing, by the computing system, the attributes from each respective ATM of the plurality of ATMs to historical ATM usage statistics of the user; and

interfacing, with the user, via a dialog message session generated on the interface of the client device and via a chat bot generated by the application, to route the user of the client device to the target ATM from the plurality of ATMs based at least partially on the historical ATM usage statistics.

2. The method of claim 1 , wherein receiving, by the computing system from the client device, the request to locate the target ATM comprises:
receiving, by the computing system, a text message from the client device; and
analyzing, by the computing system, the text message to identify the request contained therein.

3. The method of claim 1 , wherein the constraint of the desired ATM comprises at least one or more of a maximum distance of the ATM from the location of the client device, a type of ATM, a fee-free ATM, an in-store ATM, and a no-limit ATM.

4. The method of claim 1 , wherein identifying, by the computing system, the attributes associated with each respective ATM of the plurality of ATMs proximate the location of the client device comprises:
receiving, from each ATM, a total amount of funds available in the ATM.

5. The method of claim 1 , wherein the attributes associated with the ATMs comprise at least one or more of a fee associated with withdrawal, an increment in which funds are withdrawn, and a location of the ATM.

6. The method of claim 1 , routing, by the computing system, the user of the client device to the target ATM from the plurality of ATMs based at least partially on the historical ATM usage statistics, comprises:
routing the user to the target ATM, wherein the target ATM is scheduled to be refilled within a predefined period of the request.

7. A system associated with at least one financial institution having an ATM network, comprising:
a processor; and
a memory having programming instructions stored thereon, which, when executed by the processor, perform one or more operations comprising:
retrieving historical ATM transaction data for a plurality of users of the ATM network, wherein the historical ATM transaction data comprises, for each individual user, a user identifier and attributes of a respective ATM associated with each historical ATM transaction executed by that user;
training, using a machine learning module, a plurality of prediction models, to learn individualized user ATM habits based on training sets comprising the historical ATM transaction data for each user;
storing in a database, for each user, the user identifier, the historical ATM transactions for the user and the prediction model for predicting the individualized ATM habits of the user and the attributes of the ATMs the user frequents, wherein the user's ATMs comprise ATMs associated with the financial institution and third party ATMs;
receiving, from a client device associated with a user, a request to locate a target ATM, wherein the request comprises a constraint of the ATM, wherein the system is in electronic communication with an application installed on the client device for providing location services and electronic dialog messaging services to the system, wherein the request is generated by the user using an interface generated on the client device by the application;
determining, based on the request, the user identifier associated with the user and the location of the client device;
accessing, from the database and based on the determined user identifier, the prediction model associated with the user;
identifying a plurality of ATMs proximate the location of the client device based on the constraint, wherein the plurality of identified ATMs are selected from a group comprising financial institution ATMs and third party ATMs;

generating, via the user's individual prediction model, a personalized ATM recommendation for the user by:
prompting, via the interface on the client device, the user to enter parameters associated with the user's desired transaction;
identifying, based on the user's entered parameters, current attributes associated with each respective ATM of a plurality of ATMs proximate the location of the client device based on the constraint, wherein the system, in response to the request, communicates with each respective ATM to identify current attributes; and
comparing the attributes from each respective ATM to historical ATM usage statistics of the user; and

interfacing, with the client device via a chat bot, to route the user to a target ATM from the plurality of ATMs based at least partially on the historical ATM usage statistics.

8. The system of claim 7 , wherein receiving, from the client device, the request to locate the ATM comprises:
receiving an electronic message from the client device; and
analyzing the electronic message to identify the request contained therein.

9. The system of claim 7 , wherein the constraint of the target A

Assignees

• Capital One Services Llc

Inventors

• Benkreira Abdelkader M'Hamed
• Mossoba Michael
• Edwards Joshua

Classifications

• G06N20/00

  Machine learning · CPC title

• G06Q20/1085 Primary

  involving automatic teller machines [ATMs] · CPC title

• G06N5/02

  Knowledge representation; Symbolic representation · CPC title