Artificial intelligence modeling to predict electronic account data

Patent metadata

Field	Value
Publication number	US-2024046333-A1
Application number	US-202318488938-A
Country	US
Kind code	A1
Filing date	Oct 17, 2023
Priority date	Apr 16, 2020
Publication date	Feb 8, 2024
Grant date	—

Abstract

Disclosed methods and system describe a server that uses AI modeling to predict negative cash flow at a user level. The server periodically retrieves data associated with the user, the data comprising monetary attributes associated with one or more accounts of the user; executes a deep neural network model trained based upon historical data associated with at least a subset of the users configured to predict a negative cash flow in one or more accounts of the user, a depth of the negative cash flow, and a duration of the negative cash flow; transmits, to a second server, the predicted values, whereby when the second server determines that a likelihood of account needs satisfies a threshold, the second server establishes an electronic communication session with an electronic device of the user; trains the deep neural network when the second server establishes the electronic communication session.

First claim

What we claim is:

1 . A method comprising:
generating, by a server, a training dataset comprising historical monetary data associated with a set of accounts comprising account activity of each account indicating whether each account within the set of accounts included a negative cash flow, a depth of the negative cash flow, and a duration of the negative cash flow; training, by the server, an artificial intelligence model using the training dataset; retrieving, by the server, a monetary attribute associated with an account of a user; executing, by the server, the artificial intelligence model to predict a first value indicating a negative cash flow in the account of the user, a second value indicating a depth of the negative cash flow, and a third value indicating a duration of the negative cash flow; and transmitting, by the server, an indication that at least one of the first value, the second value, or the third value satisfies a threshold.

2 . The method of claim 1 , further comprising:
transmitting, by the server to a second server, the first value, the second value, or the third value, whereby the second server:
executes an analytical model to determine a likelihood of account needs associated with the account of the user; and
establishes an electronic communication session with an electronic device of the user.

3 . The method of claim 1 , wherein the server further retrieves user attributes associated with the user other than the monetary attribute associated with the account of the user, wherein the server applies the retrieved user attributes to the artificial intelligence model.

4 . The method of claim 3 , wherein the user attributes comprise at least one of user's demographic data, user's income data, or the user's account type.

5 . The method of claim 1 , further comprising:
identifying, by the server, the first value, the second value, or the third value as correct predictions.

6 . The method of claim 5 , further comprising:
training, by the server, the artificial intelligence model based on the correct predictions.

7 . The method of claim 1 , wherein the artificial intelligence model is a deep neural network.

8 . The method of claim 2 , wherein the second server identifies a product to be offered to the user based on the likelihood of account needs.

9 . The method of claim 1 , wherein the server is associated with a call center, and wherein the server establishes an electronic communication session with an electronic device of the user by routing a call received from the electronic device of the user based on at least one of the first value, the second value, or the third value.

10 . The method of claim 1 , further comprising:
denying, by the server, at least one transaction associated with the user.

11 . A system comprising:
a computer-readable medium having a set of instructions that when executed cause a processor to:
generate a training dataset comprising historical monetary data associated with a set of accounts comprising account activity of each account indicating whether each account within the set of accounts included a negative cash flow, a depth of the negative cash flow, and a duration of the negative cash flow;
train an artificial intelligence model using the training dataset;
retrieve a monetary attribute associated with an account of a user;
execute the artificial intelligence model to predict a first value indicating a negative cash flow in the account of the user, a second value indicating a depth of the negative cash flow, and a third value indicating a duration of the negative cash flow; and
transmit an indication that at least one of the first value, the second value, or the third value satisfies a threshold.

12 . The system of claim 11 , wherein the set of instructions further cause the processor to
transmit, to a second server, the first value, the second value, or the third value, whereby the second server:
executes an analytical model to determine a likelihood of account needs associated with the account of the user; and
establishes an electronic communication session with an electronic device of the user.

13 . The system of claim 11 , wherein the server further retrieves user attributes associated with the user other than the monetary attribute associated with the account of the user, wherein the server applies the retrieved user attributes to the artificial intelligence model.

14 . The system of claim 13 , wherein the user attributes comprise at least one of user's demographic data, user's income data, or the user's account type.

15 . The system of claim 11 , wherein the set of instructions further cause the processor to:
identify the first value, the second value, or the third value as correct predictions.

16 . The system of claim 15 , wherein the set of instructions further cause the processor to:
Train the artificial intelligence model based on the correct predictions.

17 . The system of claim 11 , wherein the artificial intelligence model is a deep neural network.

18 . The system of claim 12 , wherein the second server identifies a product to be offered to the user based on the likelihood of account needs.

19 . The system of claim 12 , wherein the server is associated with a call center, and wherein the server establishes an electronic communication session with an electronic device of the user by routing a call received from the electronic device of the user based on at least one of the first value, the second value, or the third value.

20 . The system of claim 11 , wherein the set of instructions further cause the processor to:
deny at least one transaction associated with the user.

Assignees

• Bank Of Montreal

Inventors

• Nosrati Seyed Masoud
• Vahlis Evgene
• Shahir Seyed Hamed Yaghoubi
• Zhao Bo
• Langballe Nicole
• Poon Peter

Classifications

• G06N3/09

  Supervised learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/098

  Distributed learning, e.g. federated learning · CPC title

• G06Q30/0631 Primary

  Recommending goods or services · CPC title

• G06N3/04

  Architecture, e.g. interconnection topology · CPC title