Life event bank ledger

Patent metadata

Field	Value
Publication number	US-11538116-B2
Application number	US-202117222609-A
Country	US
Kind code	B2
Filing date	Apr 5, 2021
Priority date	Dec 4, 2019
Publication date	Dec 27, 2022
Grant date	Dec 27, 2022

Abstract

A system and method for generating a ledger is disclosed herein. A computing system receives, from one or more third party vendors, a plurality of transactions associated with a user. The computing system parses the plurality of transactions to identify one or more parameters associated with each transaction of the plurality of transactions. The computing system groups the one or more transactions into one or more clusters based on the identified one or more parameters. The computing system associates a life event to each cluster of the one or more clusters. The computing system interfaces with a client device associated with the user to confirm an associated life event. Upon receiving a confirmation from the user regarding the associated life event, the computing system generates a ledger. The ledger includes the life event and the one or more transactions associated therewith.

First claim

What is claimed:

1. A method, comprising:
anonymizing, by a computing system, a plurality of transactions associated with a plurality of users;
generating, by the computing system, a prediction model to identify groups of related transactions by:
training, by the computing system, the prediction model to identify for a respective user, based on the anonymized plurality of transactions, a subset of the respective user's transactions that are related to each other;
testing, by the computing system, the prediction model to identify a success ratio of the training, wherein the success ratio corresponds to a threshold level of accuracy; and
retraining and retesting, by the computing system, the prediction model until the prediction model groups the subset of transactions in accordance with the threshold level of accuracy;

retrieving, by the computing system, a set of target transactions associated with a target user;
grouping, by the computing system and based on the prediction model identifying relatedness to each other, one or more transactions of the set of target transactions into a cluster; and
associating, by the computing system, a life event to the cluster of the one or more transactions;
generating, by the computing system, an interactive graphical user interface comprising an indication of the life event and corresponding cluster associated with the life event; and
causing, by the computing system, a client device associated with the target user to display the interactive graphical user interface.

2. The method of claim 1 , further comprising:
interfacing, by the computing system, with the client device associated with the target user to confirm the life event.

3. The method of claim 2 , wherein interfacing, by the computing system, with the client device associated with the target user to confirm the life event, comprises:
activating an interactive agent configured to interact with the client device;
generating, by the interactive agent, a confirmation message to be transmitted to the client device, the confirmation message seeking to confirm the life event; and
sending, by the interactive agent, the confirmation message to the client device.

4. The method of claim 3 , wherein sending, by the interactive agent, the confirmation message to confirm the life event, comprises:
sending, by the interactive agent, the confirmation message as a text message to a text message application executing on the client device.

5. The method of claim 1 , further comprising:
generating, by the computing system, a plurality of synthetic transactions configured to mimic real transactions.

6. The method of claim 5 , further comprising:
further training, by the computing system, the prediction model to identify for the respective user, based on the plurality of synthetic transactions, a subset of the respective user's transactions that are related to each other.

7. The method of claim 1 , further comprising:
receiving, by the computing system from the client device, an indication from the target user regarding a modification to the life event; and
re-assessing, by the computing system, the one or more transactions associated with the cluster to generate a new cluster.

8. A method, comprising:
identifying, by a computing system, a plurality of transactions associated with a plurality of users;
anonymizing, by the computing system, the plurality of transactions;
generating, by the computing system, a plurality of synthetic transactions configured to mimic real transactions;
generating, by the computing system, a prediction model to identify groups of related transactions by:
training, by the computing system, the prediction model to identify, based on the plurality of transactions and the plurality of synthetic transactions, a subset of transactions related to each other;
testing, by the computing system, the prediction model to identify a success ratio of the training, wherein the success ratio corresponds to a threshold level of accuracy; and
retraining and retesting, by the computing system, the prediction model until the prediction model groups transactions in accordance with the threshold level of accuracy;

retrieving, by the computing system, a set of target transactions associated with a target user;
grouping, by the computing system via the prediction model, one or more transactions of the set of target transactions into a cluster; and
associating, by the computing system, a life event to the cluster of the one or more transactions.

9. The method of claim 8 , further comprising:
interfacing, by the computing system, with a client device associated with the target user to confirm the cluster.

10. The method of claim 9 , wherein interfacing, by the computing system, with the client device associated with the target user to confirm the cluster, comprises:
activating an interactive agent configured to interact with the client device;
generating, by the interactive agent, a confirmation message to be transmitted to the client device, the confirmation message seeking to confirm the cluster; and
sending, by the interactive agent, the confirmation message to the client device.

11. The method of claim 10 , wherein sending, by the interactive agent, the confirmation message to confirm the cluster, comprises:
sending, by the interactive agent, the confirmation message as a text message to a text message application executing on the client device.

12. The method of claim 8 , further comprising:
generating, by the computing system, a plurality of synthetic transactions configured to mimic real transactions.

13. The method of claim 12 , further comprising:
further training, by the computing system, the prediction model to identify for the respective user, based on the plurality of synthetic transactions, a subset of the respective user's transactions that are related to each other.

14. The method of claim 8 , further comprising:
receiving, by the computing system from a client device, an indication from the target user regarding a modification to the life event; and
re-assessing, by the computing system, the one or more transactions associated with the cluster to generate a new cluster.

15. A system, comprising:
a processor in communication with one or more client devices associated with one or more users; and
a memory having programming instructions stored thereon, which, when executed by the processor, performs operations comprising:
anonymizing a plurality of transactions associated with a plurality of users;
generating a prediction model to identify groups of related transactions by:
training the prediction model to identify for a respective user, based on the anonymized plurality of transactions, a subset of the respective user's transactions that are related to each other;
testing the prediction model to identify a success ratio of the training, wherein the success ratio corresponds to a threshold level of accuracy; and
retraining and retesting the prediction model until the prediction model groups transactions in accordance with the threshold level of accuracy;

retrieving a set of target transactions associated with a target user;
grouping, based on the prediction model identifying relatedness to each other, one or more transactions of the set of target transactions into a cluster; and
associating a life event to the cluster.

16. The system of claim 15 , wherein the operations further comprise:
interfacing with a client device associated with the target user to confirm the cluster.

17. The system of claim 16 ,

Assignees

• Capital One Services Llc

Inventors

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

Classifications

• G06N20/00

  Machine learning · CPC title

• G06Q40/12 Primary

  Accounting · CPC title

• G06F16/21

  Design, administration or maintenance of databases · CPC title